chore: bump version to 0.12.16

The `map`, `join`, and `contains` expression filters assumed their
argument was a string. A non-string argument — an authoring mistake such
as `| map(5)`, `| join(5)`, or `| contains(5)` — reached an operation
that only strings support and raised a cryptic exception that escaped the
evaluator entirely:

  * `map(5)`      -> `attr.split(".")`  -> AttributeError
  * `join(5)`     -> `separator.join(...)` -> AttributeError
  * `contains(5)` on a string value -> `x in str` -> TypeError

The engine wraps neither expression evaluation nor `step_impl.execute()`
in a try/except, so each of these took down the whole run with a message
that names none of the real problem.

Validate the argument type up front and raise a `ValueError` naming the
filter and the offending type instead, mirroring the strict argument
handling already in `from_json`. `contains` guards only the string-value
branch: for a list value, membership of any element type is legitimate
(`5 in [1, 2, 5]`), so that branch is intentionally left unguarded.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.github/CODEOWNERS

@@ -5,4 +5,3 @@
 /extensions/catalog.community.json @mnriem
 /integrations/catalog.community.json @mnriem
 /presets/catalog.community.json @mnriem
-

.github/ISSUE_TEMPLATE/agent_request.yml

@@ -7,7 +7,7 @@ body:
     attributes:
       value: |
         Thanks for requesting a new agent! Before submitting, please check if the agent is already supported.
-        
+
         **Currently supported agents**: Amp, Antigravity, Auggie CLI, Claude Code, Cline, CodeBuddy, Codex CLI, Cursor, Devin for Terminal, Firebender, Forge, Gemini CLI, GitHub Copilot, Goose, Hermes Agent, IBM Bob, Junie, Kilo Code, Kimi Code, Kiro CLI, Lingma, Mistral Vibe, Oh My Pi, opencode, Pi Coding Agent, Qoder CLI, Qwen Code, RovoDev ACLI, SHAI, Tabnine CLI, Trae, ZCode, Zed
 
   - type: input

.github/ISSUE_TEMPLATE/extension_submission.yml

@@ -7,7 +7,7 @@ body:
     attributes:
       value: |
         Thanks for contributing an extension! This template helps you submit your extension to the community catalog.
-        
+
         **Before submitting:**
         - Review the [Extension Publishing Guide](https://github.com/github/spec-kit/blob/main/extensions/EXTENSION-PUBLISHING-GUIDE.md)
         - Ensure your extension has a valid `extension.yml` manifest
@@ -209,9 +209,9 @@ body:
         **Tested on:**
         - macOS 14.0 with Spec Kit v0.1.0
         - Linux Ubuntu 22.04 with Spec Kit v0.1.0
-        
+
         **Test project:** [Link or description]
-        
+
         **Test scenarios:**
         1. Installed extension
         2. Configured settings
@@ -230,7 +230,7 @@ body:
         ```bash
         # Install extension
         specify extension add <extension-name> --from https://github.com/your-org/spec-kit-your-extension/archive/refs/tags/v1.0.0.zip
-        
+
         # Use a command
         /speckit.your-extension.command-name arg1 arg2
         ```

.github/ISSUE_TEMPLATE/preset_submission.yml

@@ -7,7 +7,7 @@ body:
     attributes:
       value: |
         Thanks for contributing a preset! This template helps you submit your preset to the community catalog.
-        
+
         **Before submitting:**
         - Review the [Preset Publishing Guide](https://github.com/github/spec-kit/blob/main/presets/PUBLISHING.md)
         - Ensure your preset has a valid `preset.yml` manifest

.github/PULL_REQUEST_TEMPLATE.md

@@ -19,4 +19,3 @@
 - [ ] I **did** use AI assistance (describe below)
 
 <!-- If you used AI, briefly describe how (e.g., "Code generated by Copilot", "Consulted ChatGPT for approach"): -->
-

.github/workflows/stale.yml

@@ -20,24 +20,24 @@ jobs:
           days-before-stale: 150
           # Days of inactivity before a stale issue or PR is closed (after being marked stale)
           days-before-close: 30
-          
+
           # Stale issue settings
           stale-issue-message: 'This issue has been automatically marked as stale because it has not had any activity for 150 days. It will be closed in 30 days if no further activity occurs.'
           close-issue-message: 'This issue has been automatically closed due to inactivity (180 days total). If you believe this issue is still relevant, please reopen it or create a new issue.'
           stale-issue-label: 'stale'
-          
+
           # Stale PR settings
           stale-pr-message: 'This pull request has been automatically marked as stale because it has not had any activity for 150 days. It will be closed in 30 days if no further activity occurs.'
           close-pr-message: 'This pull request has been automatically closed due to inactivity (180 days total). If you believe this PR is still relevant, please reopen it or create a new PR.'
           stale-pr-label: 'stale'
-          
+
           # Exempt issues and PRs with these labels from being marked as stale
           exempt-issue-labels: 'pinned,security'
           exempt-pr-labels: 'pinned,security'
-          
+
           # Only issues or PRs with all of these labels are checked
           # Leave empty to check all issues and PRs
           any-of-labels: ''
-          
+
           # Operations per run (helps avoid rate limits)
           operations-per-run: 250

.markdownlint-cli2.jsonc

@@ -26,4 +26,4 @@
   "ignores": [
     ".genreleases/"
   ]
-}
+}

.pre-commit-config.yaml

@@ -0,0 +1,12 @@
+---
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: check-executables-have-shebangs
+      - id: check-yaml
+        exclude: \.lock\.yml$
+      - id: end-of-file-fixer
+        exclude: \.lock\.yml$
+      - id: trailing-whitespace
+        exclude: \.lock\.yml$

CHANGELOG.md

@@ -2,6 +2,112 @@
 
 <!-- insert new changelog below this comment -->
 
+## [0.12.16] - 2026-07-15
+
+### Changed
+
+- fix(workflows): raise a clear error, not a cryptic crash, on non-string filter args (#3522)
+- feat(workflows): expose workflow source directory to steps (#3469)
+- fix(workflows): fan-out max_concurrency .inf falls back to sequential, not crash (#3521)
+- Update Coding Standards Drift Control extension to v0.4.0 (#3540)
+- fix(presets): seed constitution from preset constitution-template (#3272) (#3276)
+- docs: add PyPI as second supported install route (#3425) (#3516)
+- fix(workflows): fail while/do-while steps on non-list steps instead of crashing (#3519)
+- Add PatchWarden Evidence Pack extension to community catalog (#3514)
+- feat(extensions): port git extension scripts to Python (#3400)
+- chore: release 0.12.15, begin 0.12.16.dev0 development (#3513)
+
+## [0.12.15] - 2026-07-14
+
+### Changed
+
+- Update Autonomous Run Governance preset to v0.1.4 (#3511)
+- fix(workflows): raise catalog error, not raw ValueError, on a malformed catalog URL (#3484)
+- fix(workflows): evaluate 'in'/'not in' safely on a non-iterable right operand (#3447) (#3468)
+- fix: add trailing newline to init-options.json output (#3509)
+- feat(workflows): align workflow CLI with extension command surface (#3419)
+- fix(extensions): stop env-var config leaking across prefix-colliding extension IDs (#3497)
+- fix(integrations): escape control characters in goose recipe YAML renderer (#3384)
+- [extension] Update DocGuard — CDD Enforcement extension to v0.32.0 (#3489)
+- [extension] Add Multi-Repo Branch Sync extension to community catalog (#3411)
+- chore: release 0.12.14, begin 0.12.15.dev0 development (#3506)
+
+## [0.12.14] - 2026-07-13
+
+### Changed
+
+- [extension] Add Spec Kit Memory extension to community catalog (#3455)
+- Add Test-First Governance preset to community catalog (#3504)
+- Add Autonomous Run Governance preset to community catalog (#3501)
+- fix(workflows): validate command step input/options are mappings (#3262)
+- fix(presets): resolve() honors manifest-declared file: for installed presets (#3351)
+- fix(init): don't block on confirmation for 'init --here' without a TTY (#3236)
+- [extension] Add Quality Gates (Enforcement Layer) extension to community catalog (#3431)
+- fix(integrations): exit cleanly on unbalanced quote in --integration-options (#3457) (#3466)
+- fix(integrations): declare kiro-cli multi-install safe (#3471) (#3485)
+- fix(workflows): fail fan-in step on non-list wait_for instead of crashing (#3482)
+- chore: release 0.12.13, begin 0.12.14.dev0 development (#3498)
+
+## [0.12.13] - 2026-07-13
+
+### Changed
+
+- fix(workflows): fail switch step on non-mapping cases instead of crashing (#3481)
+- Cleanup agent-file-template.md (#2579)
+- fix: mark Kiro integration as multi-install safe (#3472)
+- fix: rewrite extension-relative subdir paths in generated command bodies (#3444)
+- fix(templates): point constitution sync checklist at installed command files (#3418)
+- feat(workflows): make shell step timeout configurable (#3327) (#3328)
+- docs: clarify that release tags keep the leading v prefix (#3463)
+- fix(workflows): don't crash on membership test against a non-iterable (#3448)
+- fix(workflows): if-step validate accepts falsy non-list else (#3264)
+- chore: release 0.12.12, begin 0.12.13.dev0 development (#3490)
+
+## [0.12.12] - 2026-07-13
+
+### Changed
+
+- fix(extensions): set-priority repairs corrupted boolean priority (#3268)
+- fix(presets): set-priority repairs corrupted boolean priority (#3269)
+- fix(workflows): engine loop cap ignores bool max_iterations (#3270)
+- docs(bundles): document --integration on 'bundle update' (#3271)
+- fix(workflows): harden catalog.py against mis-shaped registry & non-string fields (#3375)
+- Add Verify Review Ship extension to community catalog (#3450)
+- fix(bundle): reject file:// / local download_url — catalog URLs are HTTPS-only (#3344)
+- fix(extensions): handle prefix-colliding env vars in _get_env_config (#3350)
+- docs: document copilot skills mode (--skills) and markdown deprecation (#3313)
+- chore: release 0.12.11, begin 0.12.12.dev0 development (#3460)
+
+## [0.12.11] - 2026-07-10
+
+### Changed
+
+- fix(agent-context): discover nested plan.md in scoped layouts (#3024) (#3301)
+- fix(auth): return no matches, not raw ValueError, for a malformed URL (#3437)
+- fix(catalogs): raise catalog error, not raw ValueError, on a malformed URL (#3435)
+- fix(bundler): raise BundlerError, not raw ValueError, on a malformed catalog URL (#3433)
+- chore: add pre-commit config and fix trailing whitespace/end-of-file (#3430)
+- Add EARS Requirements Syntax extension to community catalog (#3407)
+- Add Spec Kit Figma extension to community catalog (#3408)
+- fix(workflows): report validation errors instead of crashing on non-string workflow.yml scalars (#3421)
+- fix(templates): remove self-referencing path in plan-template.md note (#3417)
+- chore: release 0.12.10, begin 0.12.11.dev0 development (#3453)
+
+## [0.12.10] - 2026-07-10
+
+### Changed
+
+- chore(deps): bump astral-sh/setup-uv from 8.2.0 to 8.3.2 (#3439)
+- chore(deps): bump DavidAnson/markdownlint-cli2-action (#3438)
+- fix(templates): correct phase numbering in plan.md (#3416)
+- fix(git-ext): honor explicit -Number 0 in PowerShell branch creation (#3412)
+- docs: add 'spectatui' entry to friends.md (#3362)
+- test: pin interpreter probe so py-template render test passes on Windows (#3428)
+- feat(workflows): make shell step timeout configurable (#3404)
+- fix: find plans in nested spec directories (#3405)
+- feat(templates): add py: lines to command templates' scripts frontmatter (#3403)
+- chore: release 0.12.9, begin 0.12.10.dev0 development (#3426)
+
 ## [0.12.9] - 2026-07-09
 
 ### Changed

LICENSE

@@ -19,4 +19,3 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
-

README.md

@@ -45,12 +45,18 @@ Spec-Driven Development **flips the script** on traditional software development
 
 ### 1. Install Specify CLI
 
-Requires **[uv](https://docs.astral.sh/uv/)** ([install uv](./docs/install/uv.md)). Replace `vX.Y.Z` with the latest tag from [Releases](https://github.com/github/spec-kit/releases):
+Requires **[uv](https://docs.astral.sh/uv/)** ([install uv](./docs/install/uv.md)). Replace `vX.Y.Z` with the latest release tag from [Releases](https://github.com/github/spec-kit/releases) — keep the leading `v` (for example, `v0.12.11`, not `0.12.11`):
 
 ```bash
 uv tool install specify-cli --from git+https://github.com/github/spec-kit.git@vX.Y.Z
 ```
 
+Prefer installing from PyPI? The `specify-cli` package is also published there:
+
+```bash
+uv tool install specify-cli
+```
+
 See the [Installation Guide](./docs/installation.md) for alternative methods, verification, upgrade, and troubleshooting.
 
 ### 2. Initialize a project

docs/.gitignore

@@ -6,4 +6,3 @@ obj/
 # Temporary files
 *.tmp
 *.log
-

docs/community/extensions.md

@@ -51,7 +51,8 @@ The following community-contributed extensions are available in [`catalog.commun
 | Confluence Extension | Create a doc in Confluence summarizing the specifications and planning files | `integration` | Read+Write | [spec-kit-confluence](https://github.com/aaronrsun/spec-kit-confluence) |
 | Cost Tracker | Track real LLM dollar cost across SDD workflows — per-feature budgets, per-integration comparison, and finance-ready exports | `visibility` | Read+Write | [spec-kit-cost](https://github.com/Quratulain-bilal/spec-kit-cost) |
 | Data Model Diagram | Generates Mermaid ER diagrams from Spec Kit data models after planning | `docs` | Read+Write | [spec-kit-data-model-diagram](https://github.com/benizzio/spec-kit-data-model-diagram) |
-| DocGuard — CDD Enforcement | The only doc-integrity engine with an MCP server, SARIF output, and a deterministic zero-LLM core. Validates, scores, and traces documentation against code — 24 validators, stable finding codes, GitHub Action with PR annotations, spec-kit hooks. Pure Node.js, one pinned dep. | `docs` | Read+Write | [spec-kit-docguard](https://github.com/raccioly/docguard) |
+| DocGuard — CDD Enforcement | Doc-integrity engine with MCP server, SARIF output, and zero-LLM core. Validates, scores, and traces documentation against code — 24 validators, stable finding codes, spec-kit hooks. Pure Node.js. | `docs` | Read+Write | [spec-kit-docguard](https://github.com/raccioly/docguard) |
+| EARS Requirements Syntax | Author, lint, and convert requirements using EARS - the five industry-standard sentence patterns for unambiguous, testable requirements | `docs` | Read+Write | [spec-kit-ears](https://github.com/dhruv-15-03/spec-kit-ears) |
 | Extensify | Create and validate extensions and extension catalogs | `process` | Read+Write | [extensify](https://github.com/mnriem/spec-kit-extensions/tree/main/extensify) |
 | Fix Findings | Automated analyze-fix-reanalyze loop that resolves spec findings until clean | `code` | Read+Write | [spec-kit-fix-findings](https://github.com/Quratulain-bilal/spec-kit-fix-findings) |
 | FixIt Extension | Spec-aware bug fixing — maps bugs to spec artifacts, proposes a plan, applies minimal changes | `code` | Read+Write | [spec-kit-fixit](https://github.com/speckit-community/spec-kit-fixit) |
@@ -83,12 +84,14 @@ The following community-contributed extensions are available in [`catalog.commun
 | MemoryLint | Evidence-driven instruction drift checker: audits agent memory files for boundary, reality, conflict, and redundancy drift. | `process` | Read+Write | [memorylint](https://github.com/RbBtSn0w/spec-kit-extensions/tree/main/memorylint) |
 | Microsoft 365 Integration | Fetch Teams messages, meeting transcripts, and SharePoint/OneDrive files as local Markdown for spec generation | `integration` | Read+Write | [spec-kit-m365](https://github.com/BenBtg/spec-kit-m365) |
 | Multi-Model Review | Cross-model Spec Kit handoffs for spec authoring, implementation routing, and review. | `process` | Read+Write | [multi-model-review](https://github.com/formin/multi-model-review) |
+| Multi-Repo Branch Sync | Creates the feature branch in affected sub-repositories and git submodules via plan/tasks hooks | `process` | Read+Write | [multi-repo-sync](https://github.com/fyloss/spec-kit-multi-repo-sync) |
 | Multi-Sites Spec Kit | Multi-site aware specify command with per-site spec folders, auto-increment, and Drupal support | `process` | Read+Write | [spec-kit-multi-sites](https://github.com/teeyo/spec-kit-multi-sites) |
 | .NET Framework to Modern .NET Migration | Orchestrate end-to-end .NET Framework to modern .NET migration across 7 phases, with SDD lifecycle integration | `process` | Read+Write | [spec-kit-fx-to-net](https://github.com/RogerBestMsft/spec-kit-FxToNet) |
 | Onboard | Contextual onboarding and progressive growth for developers new to spec-kit projects. Explains specs, maps dependencies, validates understanding, and guides the next step | `process` | Read+Write | [spec-kit-onboard](https://github.com/dmux/spec-kit-onboard) |
 | Optimize | Audit and optimize AI governance for context efficiency — token budgets, rule health, interpretability, compression, coherence, and echo detection | `process` | Read+Write | [spec-kit-optimize](https://github.com/sakitA/spec-kit-optimize) |
 | Orchestration Task Context Management | Adds subagent work-unit orchestration to generated Spec Kit task files | `process` | Read+Write | [spec-kit-orchestration-task-context-management](https://github.com/benizzio/spec-kit-orchestration-task-context-management) |
 | OWASP LLM Threat Model | OWASP Top 10 for LLM Applications 2025 threat analysis on agent artifacts | `code` | Read-only | [spec-kit-threatmodel](https://github.com/NaviaSamal/spec-kit-threatmodel) |
+| PatchWarden Evidence Pack | Map Spec Kit tasks into a guarded PatchWarden Goal and export bounded, traceable evidence for an accepted lineage. | `process` | Read+Write | [spec-kit-patchwarden](https://github.com/jiezeng2004-design/spec-kit-patchwarden) |
 | Plan Review Gate | Require spec.md and plan.md to be merged via MR/PR before allowing task generation | `process` | Read-only | [spec-kit-plan-review-gate](https://github.com/luno/spec-kit-plan-review-gate) |
 | PR Bridge | Auto-generate pull request descriptions, checklists, and summaries from spec artifacts | `process` | Read-only | [spec-kit-pr-bridge-](https://github.com/Quratulain-bilal/spec-kit-pr-bridge-) |
 | Presetify | Create and validate presets and preset catalogs | `process` | Read+Write | [presetify](https://github.com/mnriem/spec-kit-extensions/tree/main/presetify) |
@@ -97,6 +100,7 @@ The following community-contributed extensions are available in [`catalog.commun
 | Project Health Check | Diagnose a Spec Kit project and report health issues across structure, agents, features, scripts, extensions, and git | `visibility` | Read-only | [spec-kit-doctor](https://github.com/KhawarHabibKhan/spec-kit-doctor) |
 | Project Status | Show current SDD workflow progress — active feature, artifact status, task completion, workflow phase, and extensions summary | `visibility` | Read-only | [spec-kit-status](https://github.com/KhawarHabibKhan/spec-kit-status) |
 | QA Testing Extension | Systematic QA testing with browser-driven or CLI-based validation of acceptance criteria from spec | `code` | Read-only | [spec-kit-qa](https://github.com/arunt14/spec-kit-qa) |
+| Quality Gates (Enforcement Layer) | Deterministic quality enforcement for Spec Kit projects at three boundaries — agent hooks, git pre-commit, CI — with one policy file and provable enforcement (attestations, canaries, verified parity). | `process` | Read+Write | [spec-gates](https://github.com/schwichtgit/spec-gates) |
 | RAG Azure Builder | Spec Kit extension for onboarding and operating an Azure RAG stack with guided workflows. | `process` | Read+Write | [spec-kit-extension-rag-azure-builder](https://github.com/Sertxito/spec-kit-extension-rag-azure-builder) |
 | Ralph Loop | Autonomous implementation loop using AI agent CLI | `code` | Read+Write | [spec-kit-ralph](https://github.com/Rubiss-Projects/spec-kit-ralph) |
 | Reconcile Extension | Reconcile implementation drift by surgically updating feature artifacts. | `docs` | Read+Write | [spec-kit-reconcile](https://github.com/stn1slv/spec-kit-reconcile) |
@@ -117,6 +121,8 @@ The following community-contributed extensions are available in [`catalog.commun
 | Spec Critique Extension | Dual-lens critical review of spec and plan from product strategy and engineering risk perspectives | `docs` | Read-only | [spec-kit-critique](https://github.com/arunt14/spec-kit-critique) |
 | Spec Diagram | Auto-generate Mermaid diagrams of SDD workflow state, feature progress, and task dependencies | `visibility` | Read-only | [spec-kit-diagram-](https://github.com/Quratulain-bilal/spec-kit-diagram-) |
 | Spec Kit Discovery Extension | Run technical discovery commands for feasibility, technology selection, scenario-specific technical decisions, legacy codebase assessment, implementation understanding, and proof-of-concept validation | `process` | Read+Write | [spec-kit-discovery](https://github.com/bigsmartben/spec-kit-discovery) |
+| Spec Kit Figma | Agent-agnostic SpecKit extension that grounds spec, plan & task generation in Figma design context — REST + optional MCP, single/mono/multi-repo, macOS/Linux/Windows. | `integration` | Read+Write | [spec-kit-figma](https://github.com/Fyloss/spec-kit-figma) |
+| Spec Kit Memory | Recalls prior specs and decisions from configurable memory tools (e.g. memsearch) before SDLC stages, so planning and specification start from what the project already knows | `docs` | Read+Write | [spec-kit-memory](https://github.com/zaytsevand/spec-kit-memory) |
 | Spec Kit Preview | Generate evidence-backed low, mid, or high fidelity previews from Spec Kit artifacts as Markdown or self-contained HTML | `docs` | Read+Write | [spec-kit-preview](https://github.com/bigsmartben/spec-kit-preview) |
 | Spec Kit Schedule | Optimal multi-agent task scheduling via CP-SAT — DAG precedence, hallucination-aware caps, file-conflict avoidance, stochastic durations, replanning, and interactive HTML output | `process` | Read+Write | [spec-kit-schedule](https://github.com/jfranc38/spec-kit-schedule) |
 | Spec Kit TLDR | Render a feature's spec.md / plan.md into a review-oriented TLDR (self-contained HTML dashboard + PR-native Markdown) that surfaces risks for faster PR review. | `visibility` | Read+Write | [speckit-tldr](https://github.com/qurore/speckit-tldr) |
@@ -146,6 +152,7 @@ The following community-contributed extensions are available in [`catalog.commun
 | Token Economy | Token routing, measured savings, and context audit workflows | `process` | Read+Write | [spec-kit-token-economy](https://github.com/formin/spec-kit-token-economy) |
 | V-Model Extension Pack | Enforces V-Model paired generation of development specs and test specs with full traceability | `docs` | Read+Write | [spec-kit-v-model](https://github.com/leocamello/spec-kit-v-model) |
 | Verify Extension | Post-implementation quality gate that validates implemented code against specification artifacts | `code` | Read-only | [spec-kit-verify](https://github.com/ismaelJimenez/spec-kit-verify) |
+| Verify Review Ship | Adds post-implementation verify, review, and ship readiness gates to Spec Kit workflows | `process` | Read-only | [spec-kit-verify-review-ship](https://github.com/cadugevaerd/spec-kit-verify-review-ship) |
 | Verify Tasks Extension | Detect phantom completions: tasks marked [X] in tasks.md with no real implementation | `code` | Read-only | [spec-kit-verify-tasks](https://github.com/datastone-inc/spec-kit-verify-tasks) |
 | Version Guard | Verify tech stack versions against live npm registries before planning and implementation | `process` | Read-only | [spec-kit-version-guard](https://github.com/KevinBrown5280/spec-kit-version-guard) |
 | What-if Analysis | Preview the downstream impact (complexity, effort, tasks, risks) of requirement changes before committing to them | `visibility` | Read-only | [spec-kit-whatif](https://github.com/DevAbdullah90/spec-kit-whatif) |

docs/community/presets.md

@@ -11,6 +11,7 @@ The following community-contributed presets customize how Spec Kit behaves — o
 | Agent Parity Governance | Adds shared-guidance parity, audit-ready Spec-Kit run evidence, and agent-neutral model-routing guidance across a project's declared AI-agent instruction surfaces so agent guidance does not drift. | 6 templates, 3 commands | — | [spec-kit-preset-agent-parity-governance](https://github.com/hindermath/spec-kit-preset-agent-parity-governance) |
 | AIDE In-Place Migration | Adapts the AIDE extension workflow for in-place technology migrations (X → Y pattern) — adds migration objectives, verification gates, knowledge documents, and behavioral equivalence criteria | 2 templates, 8 commands | AIDE extension | [spec-kit-presets](https://github.com/mnriem/spec-kit-presets) |
 | Architecture Governance | Adds secure software architecture, STRIDE+CAPEC threat modeling, arc42 security cross-cutting concepts, S-ADRs, Zero Trust applicability, OWASP SAMM governance, BSI C3A cloud autonomy, BSI C5 cloud compliance assurance, and audit-ready Spec Kit run evidence | 13 templates, 3 commands | — | [spec-kit-preset-architecture-governance](https://github.com/hindermath/spec-kit-preset-architecture-governance) |
+| Autonomous Run Governance | Adds permission-bounded, evidence-first governance for autonomous Spec Kit delivery, convergence, resume, closeout, and retrospective learning. | 12 templates, 2 commands, 2 scripts | — | [spec-kit-preset-autonomous-run-governance](https://github.com/hindermath/spec-kit-preset-autonomous-run-governance) |
 | Canon Core | Adapts original Spec Kit workflow to work together with Canon extension | 2 templates, 8 commands | — | [spec-kit-canon](https://github.com/maximiliamus/spec-kit-canon) |
 | Claude AskUserQuestion | Upgrades `/speckit.clarify` and `/speckit.checklist` on Claude Code from Markdown-table prompts to the native AskUserQuestion picker, with a recommended option and reasoning on every question | 2 commands | — | [spec-kit-preset-claude-ask-questions](https://github.com/0xrafasec/spec-kit-preset-claude-ask-questions) |
 | Command Density | Compacts the nine core Spec Kit command prompts while preserving scripts, handoffs, placeholders, hook output blocks, and rule structure | 9 commands | — | [spec-kit-preset-command-density](https://github.com/Xopoko/spec-kit-preset-command-density) |
@@ -28,6 +29,7 @@ The following community-contributed presets customize how Spec Kit behaves — o
 | SicarioSpec Core | Baseline secure-by-default Spec Kit governance profile. | 5 templates | — | [sicario-spec](https://github.com/dfirs1car1o/sicario-spec) |
 | Spec2Cloud | Spec-driven workflow tuned for shipping to Azure: spec → plan → tasks → implement → deploy | 5 templates, 8 commands | — | [spec2cloud](https://github.com/Azure-Samples/Spec2Cloud) |
 | Table of Contents Navigation | Adds a navigable Table of Contents to generated spec.md, plan.md, and tasks.md documents | 3 templates, 3 commands | — | [spec-kit-preset-toc-navigation](https://github.com/Quratulain-bilal/spec-kit-preset-toc-navigation) |
+| Test-First Governance | Governs TDD with coverage-complete BDD/ATDD Gherkin scenarios, explicit suite ownership, professional test reports, traceability, and risk-based quality gates. | 10 templates, 8 commands | — | [spec-kit-preset-test-first-governance](https://github.com/ka-zo/spec-kit-preset-test-first-governance) |
 | VS Code Ask Questions | Enhances the clarify command to use `vscode/askQuestions` for batched interactive questioning. | 1 command | — | [spec-kit-presets](https://github.com/fdcastel/spec-kit-presets) |
 | Workflow Preset | Behavior-first specification, design artifacts, and agent-native handoff orchestration — adds requirement-phase behavior drafts, formal BDD/UIF/behavior contracts, optional design artifacts, and scoped implementation handoffs with Core Agent, Vertical Planner Agent, and Worker Agent modes | 22 templates, 8 commands | — | [spec-kit-workflow-preset](https://github.com/bigsmartben/spec-kit-workflow-preset) |
 

docs/install/one-time.md

@@ -11,7 +11,8 @@ If you want to try Spec Kit without installing it permanently, use `uvx` to run
 # Create a new project (latest from main)
 uvx --from git+https://github.com/github/spec-kit.git specify init <PROJECT_NAME>
 
-# Or target a specific release (replace vX.Y.Z with a tag from Releases)
+# Or target a specific release (replace vX.Y.Z with a tag from Releases;
+# keep the leading v, e.g. v0.12.11 not 0.12.11)
 uvx --from git+https://github.com/github/spec-kit.git@vX.Y.Z specify init <PROJECT_NAME>
 
 # Initialize in the current directory

docs/install/pipx.md

@@ -7,7 +7,8 @@
 Pin a specific release tag for stability (check [Releases](https://github.com/github/spec-kit/releases) for the latest):
 
 ```bash
-# Install a specific stable release (recommended — replace vX.Y.Z with the latest tag)
+# Install a specific stable release (recommended — replace vX.Y.Z with the
+# latest tag, keeping the leading v, e.g. v0.12.11 not 0.12.11)
 pipx install git+https://github.com/github/spec-kit.git@vX.Y.Z
 
 # Or install latest from main (may include unreleased changes)

docs/install/pypi.md

@@ -0,0 +1,83 @@
+# Installing from PyPI
+
+Spec Kit is published to PyPI as [`specify-cli`](https://pypi.org/project/specify-cli/), maintained by the Spec Kit maintainers. Installing from PyPI is the second supported install route alongside installing from the [GitHub source](../installation.md#install-from-source--persistent-installation-recommended). Use whichever fits your workflow — both provide the same `specify` CLI.
+
+> [!NOTE]
+> The PyPI release version tracks the GitHub release tags (for example, PyPI `0.12.11` corresponds to the `v0.12.11` tag). `specify version` is only a local version/runtime sanity check — it reports the installed version but not where the `specify` executable came from, so it cannot distinguish a PyPI install from a Git install. To confirm the install source, inspect the source metadata your package manager records: `pipx list --json` reports the exact install specification for each tool, and for uv/pip installs you can check the package's [PEP 610](https://peps.python.org/pep-0610/) `direct_url.json` inside its `*.dist-info` directory (a Git or URL install records the repository/archive URL there, while a plain PyPI index install does not create that file). Note that `pip show specify-cli` only prints package metadata and will not see uv/pipx-managed environments from the host interpreter.
+
+## Install Specify CLI
+
+Use whichever Python tool you already have:
+
+```bash
+# Using uv (recommended)
+uv tool install specify-cli
+
+# Or using pipx
+pipx install specify-cli
+
+# Or using pip
+pip install specify-cli
+```
+
+### Install a specific release
+
+Pin an exact version for reproducible installs (check [PyPI](https://pypi.org/project/specify-cli/#history) or [Releases](https://github.com/github/spec-kit/releases) for available versions):
+
+```bash
+# Using uv
+uv tool install specify-cli==0.12.11
+
+# Or using pipx
+pipx install specify-cli==0.12.11
+
+# Or using pip
+pip install specify-cli==0.12.11
+```
+
+## Verify
+
+```bash
+specify version
+```
+
+## Initialize a project
+
+```bash
+specify init <PROJECT_NAME> --integration copilot
+```
+
+## Upgrade
+
+Upgrade by reinstalling the package through the same tool you used for the original install. If you originally pinned a version, note that `uv tool upgrade` preserves that pin; to move to the newest PyPI release, use an unpinned install command so you do not keep the existing version pin:
+
+```bash
+# Using uv
+uv tool install --force specify-cli
+
+# Or using pipx
+pipx install --force specify-cli
+
+# Or using pip
+pip install --upgrade specify-cli
+```
+
+> [!NOTE]
+> `specify self upgrade` currently rebuilds `uv tool` and `pipx` installs from the GitHub source release URL rather than preserving a PyPI-based installation. If you want to stay on the PyPI route, use the package-manager commands above. A plain `pip install specify-cli` is treated as an unmanaged install — upgrade it with `pip install --upgrade specify-cli`. See the [Upgrade Guide](../upgrade.md) for details.
+
+## Uninstall
+
+```bash
+# Using uv
+uv tool uninstall specify-cli
+
+# Or using pipx
+pipx uninstall specify-cli
+
+# Or using pip
+pip uninstall specify-cli
+```
+
+## Next steps
+
+Head to the [Quick Start](../quickstart.md) to initialize your first project.

docs/installation.md

@@ -11,11 +11,16 @@
 ## Installation
 
 > [!IMPORTANT]
-> The only official, maintained packages for Spec Kit come from the [github/spec-kit](https://github.com/github/spec-kit) GitHub repository. Any packages with the same name available on PyPI (e.g. `specify-cli` on pypi.org) are **not** affiliated with this project and are not maintained by the Spec Kit maintainers. For normal installs, use the GitHub-based commands shown below. For offline or air-gapped environments, locally built wheels created from this repository are also valid.
+> Spec Kit is distributed through two official channels, both published and maintained by the Spec Kit maintainers: the [github/spec-kit](https://github.com/github/spec-kit) GitHub repository (source installs) and the [`specify-cli`](https://pypi.org/project/specify-cli/) package on [PyPI](https://pypi.org/project/specify-cli/). Either route is supported for normal installs — use the commands shown below. After installing, run `specify version` as a local version/runtime sanity check. It confirms that the `specify` command is available and reports its version, but it does not prove whether the executable came from PyPI or GitHub. For offline or air-gapped environments, locally built wheels created from this repository are also valid.
 
-### Persistent Installation (Recommended)
+Spec Kit supports two install routes:
 
-Install once and use everywhere. Replace `vX.Y.Z` with a tag from [Releases](https://github.com/github/spec-kit/releases):
+1. **Install from source (GitHub)** — the recommended route, pinned to a release tag.
+2. **Install from PyPI** — install the published `specify-cli` package with your usual Python tooling.
+
+### Install from Source — Persistent Installation (Recommended)
+
+Install once and use everywhere. Replace `vX.Y.Z` with a release tag from [Releases](https://github.com/github/spec-kit/releases) — keep the leading `v` (for example, `v0.12.11`, not `0.12.11`):
 
 > [!NOTE]
 > The command below requires **[uv](https://docs.astral.sh/uv/)**. If you see `command not found: uv`, [install uv first](./install/uv.md).
@@ -30,12 +35,30 @@ Then initialize a project:
 specify init <PROJECT_NAME> --integration copilot
 ```
 
+### Install from PyPI
+
+Spec Kit is also published to PyPI as [`specify-cli`](https://pypi.org/project/specify-cli/), so you can install it with your preferred Python package manager without referencing the Git URL:
+
+```bash
+# Using uv (recommended)
+uv tool install specify-cli
+
+# Or using pipx
+pipx install specify-cli
+
+# Or using pip
+pip install specify-cli
+```
+
+To install a specific release, pin the version — for example `uv tool install specify-cli==0.12.11`. See the [PyPI installation guide](install/pypi.md) for details, including how to upgrade.
+
 ### One-time Usage
 
 Run directly without installing — see the [One-time usage (uvx)](install/one-time.md) guide.
 
 ### Alternative Package Managers
 
+- **PyPI** — see the [PyPI installation guide](install/pypi.md)
 - **pipx** — see the [pipx installation guide](install/pipx.md)
 - **Enterprise / Air-Gapped** — see the [air-gapped installation guide](install/air-gapped.md)
 
@@ -81,13 +104,13 @@ specify init <project_name> --integration claude --ignore-agent-tools
 
 ## Verification
 
-After installation, run the following command to confirm the correct version is installed:
+After installation, run the following command as a local version/runtime check:
 
 ```bash
 specify version
 ```
 
-This helps verify you are running the official Spec Kit build from GitHub, not an unrelated package with the same name.
+This confirms that the `specify` command is available and reporting the expected version. It does not prove whether that executable came from PyPI or GitHub.
 
 **Stay current:** Run `specify self check` periodically to learn whether a newer release is available — it is read-only and never modifies your installation. When you are ready to upgrade, follow the [Upgrade Guide](./upgrade.md).
 

docs/reference/bundles.md

@@ -51,10 +51,11 @@ If the current directory is not yet a Spec Kit project, `install` initializes on
 specify bundle update [<bundle_id>]
 ```
 
-| Option       | Description                          |
-| ------------ | ------------------------------------ |
-| `--all`      | Update every installed bundle        |
-| `--offline`  | Do not access the network            |
+| Option           | Description                                                                                                            |
+| ---------------- | --------------------------------------------------------------------------------------------------------------------- |
+| `--all`          | Update every installed bundle                                                                                         |
+| `--integration`  | Override the integration used when refreshing components; applied only when the project's active integration can't be determined |
+| `--offline`      | Do not access the network                                                                                             |
 
 Re-resolves a bundle and **refreshes** its components through each primitive's update path, bringing already-installed components up to the bundle's newly pinned versions while preserving primitive-level overrides (such as preset priority). Provide a bundle id, or use `--all` to update everything installed.
 

docs/reference/integrations.md

@@ -18,7 +18,7 @@ The Specify CLI supports a wide range of AI coding agents. When you run `specify
 | [Firebender](https://firebender.com/)                                                | `firebender`     | IDE-based agent for Android Studio / IntelliJ                                                                                             |
 | [Forge](https://forgecode.dev/)                                                      | `forge`          |                                                                                                                                           |
 | [Gemini CLI](https://github.com/google-gemini/gemini-cli)                            | `gemini`         |                                                                                                                                           |
-| [GitHub Copilot](https://code.visualstudio.com/)                                     | `copilot`        |                                                                                                                                           |
+| [GitHub Copilot](https://code.visualstudio.com/)                                     | `copilot`        | Defaults to legacy markdown mode: `.agent.md` command files under `.github/agents/`, companion `.prompt.md` files under `.github/prompts/`, and a `.vscode/settings.json` merge. Pass `--integration-options="--skills"` to scaffold skills as `speckit-<command>/SKILL.md` under `.github/skills/` instead. Legacy markdown mode is deprecated and will stop being the default in a future release. |
 | [Goose](https://goose-docs.ai/)                                                      | `goose`          | Uses YAML recipe format in `.goose/recipes/`                                                                                              |
 | [Hermes](https://github.com/NousResearch/hermes-agent)                               | `hermes`         | Skills-based integration; installs skills globally into `~/.hermes/skills/`                                                                |
 | [IBM Bob](https://www.ibm.com/products/bob)                                          | `bob`            | IDE-based agent                                                                                                                           |
@@ -219,6 +219,7 @@ Some integrations accept additional options via `--integration-options`:
 | ----------- | ------------------- | -------------------------------------------------------------- |
 | `generic`   | `--commands-dir`    | Required. Directory for command files                          |
 | `kimi`      | `--migrate-legacy`  | Migrate legacy `.kimi/skills/` installs to `.kimi-code/skills/` (including dotted→hyphenated skill naming, e.g. `speckit.xxx` → `speckit-xxx`) |
+| `copilot`   | `--skills`          | Scaffold commands as agent skills (`speckit-<command>/SKILL.md` under `.github/skills/`, invoked as `/speckit-<command>`) instead of the default legacy markdown mode (`.github/agents/*.agent.md` plus `.github/prompts/*.prompt.md` and a `.vscode/settings.json` merge). Without this flag, install warns that legacy markdown mode is deprecated. |
 
 Example:
 

docs/reference/workflows.md

@@ -86,8 +86,30 @@ Lists workflows installed in the current project.
 specify workflow add <source>
 ```
 
+| Option          | Description                                            |
+| --------------- | ------------------------------------------------------ |
+| `--dev`         | Install from a local workflow YAML file or directory   |
+| `--from <url>`  | Install from a custom URL (`<source>` names the expected workflow ID) |
+
 Installs a workflow from the catalog, a URL (HTTPS required), or a local file path.
 
+## Update Workflows
+
+```bash
+specify workflow update [workflow_id]
+```
+
+Updates one installed catalog workflow — or all of them when no ID is given — to the latest catalog version. Prompts for confirmation and keeps the installed copy if a download or validation fails.
+
+## Enable or Disable a Workflow
+
+```bash
+specify workflow enable <workflow_id>
+specify workflow disable <workflow_id>
+```
+
+Disabled workflows stay installed and listed (marked `[disabled]`) but refuse to run until re-enabled.
+
 ## Remove a Workflow
 
 ```bash
@@ -102,9 +124,10 @@ Removes an installed workflow from the project.
 specify workflow search [query]
 ```
 
-| Option  | Description     |
-| ------- | --------------- |
-| `--tag` | Filter by tag   |
+| Option     | Description       |
+| ---------- | ----------------- |
+| `--tag`    | Filter by tag     |
+| `--author` | Filter by author  |
 
 Searches all active catalogs for workflows matching the query.
 
@@ -282,6 +305,8 @@ Steps can reference inputs and previous step outputs using `{{ expression }}` sy
 | `inputs.spec`                  | Workflow input values                |
 | `steps.specify.output.file`    | Output from a previous step          |
 | `item`                         | Current item in a fan-out iteration  |
+| `context.run_id`               | Current workflow run ID              |
+| `context.workflow_dir`         | Resolved absolute path to the workflow source directory. Empty string for string-loaded workflows. |
 
 Available filters: `default`, `join`, `contains`, `map`, `from_json`.
 
@@ -293,6 +318,14 @@ args: "{{ inputs.spec }}"
 message: "{{ status | default('pending') }}"
 ```
 
+## Shell Step Environment Variables
+
+Shell steps automatically receive the following environment variables:
+
+| Variable | Description |
+| -------- | ----------- |
+| `SPECKIT_WORKFLOW_DIR` | Resolved absolute path to the workflow source directory (same value as `{{ context.workflow_dir }}`). Not set when the workflow has no source path. |
+
 ## Input Types
 
 | Type      | Coercion                                          |

docs/toc.yml

@@ -13,6 +13,8 @@
       href: upgrade.md
     - name: Install uv
       href: install/uv.md
+    - name: Install from PyPI
+      href: install/pypi.md
     - name: Install with pipx
       href: install/pipx.md
     - name: One-time Usage (uvx)

extensions/agent-context/commands/speckit.agent-context.update.md

@@ -15,7 +15,7 @@ The script reads the agent-context extension config at
 - `context_files` — optional project-relative paths for multiple coding agent context files. When non-empty, the script updates each listed file and the list takes precedence over `context_file`.
 - `context_markers.start` / `.end` — the delimiters surrounding the managed section. Defaults to `<!-- SPECKIT START -->` and `<!-- SPECKIT END -->` when the field is missing.
 
-It then creates, replaces, or appends the managed block so that the section points at the most recent plan path when one can be discovered (`specs/**/plan.md`, any depth).
+It then creates, replaces, or appends the managed block so that the section points at the most recent plan path when one can be discovered (any `plan.md` under `specs/`, including nested scoped layouts such as `specs/<scope>/<feature>/plan.md`).
 
 If `context_files` and `context_file` are empty, the command reports nothing to do and exits successfully. Context file paths must stay project-relative; absolute paths, Windows drive paths, backslash separators, and `..` path segments are rejected.
 
@@ -24,4 +24,4 @@ If `context_files` and `context_file` are empty, the command reports nothing to
 - **Bash**: `.specify/extensions/agent-context/scripts/bash/update-agent-context.sh [plan_path]`
 - **PowerShell**: `.specify/extensions/agent-context/scripts/powershell/update-agent-context.ps1 [plan_path]`
 
-When `plan_path` is omitted, the script auto-detects the most recently modified `specs/**/plan.md` (any depth, so scoped layouts like `specs/<scope>/<feature>/plan.md` are found).
+When `plan_path` is omitted, the script auto-detects the most recently modified `specs/**/plan.md` (searched recursively, so nested scoped layouts are discovered).

extensions/agent-context/scripts/bash/update-agent-context.sh

@@ -307,16 +307,28 @@ import sys
 from pathlib import Path
 root = Path(sys.argv[1]).resolve()
 specs = root / "specs"
-plan = max(
-    specs.glob("**/plan.md"),
-    key=lambda p: p.stat().st_mtime,
-    default=None,
-)
-if plan:
+
+def _resolved_rel(p):
+    # Resolve symlinks before checking containment: relative_to() is lexical
+    # and would otherwise accept a plan reached through a specs/ symlink that
+    # points outside the project, emitting an in-project-looking path for an
+    # out-of-project file (or picking it as "most recent").
     try:
-        print(plan.relative_to(root).as_posix())
-    except ValueError:
-        print("")
+        return p.resolve().relative_to(root)
+    except (OSError, ValueError):
+        return None
+
+# Recurse (rather than the old one-level specs/*/plan.md glob) so scoped layouts
+# created via SPECIFY_FEATURE_DIRECTORY, e.g. specs/<scope>/<feature>/plan.md,
+# are still discovered when feature.json is absent (#3024).
+candidates = []
+for p in specs.rglob("plan.md"):
+    rel = _resolved_rel(p)
+    if rel:
+        candidates.append((p, rel))
+candidates.sort(key=lambda pr: pr[0].stat().st_mtime, reverse=True)
+if candidates:
+    print(candidates[0][1].as_posix())
 else:
     print("")
 PY

extensions/agent-context/scripts/powershell/update-agent-context.ps1

@@ -426,7 +426,11 @@ if (-not $PlanPath) {
     if (-not $PlanPath) {
         try {
             $specsDir = Join-Path $ProjectRoot 'specs'
-            $candidate = Get-ChildItem -Path $specsDir -Recurse -File -Filter 'plan.md' -ErrorAction SilentlyContinue |
+            # Recurse (rather than the old one-level specs/*/plan.md scan) so scoped
+            # layouts created via SPECIFY_FEATURE_DIRECTORY, e.g.
+            # specs/<scope>/<feature>/plan.md, are still discovered when
+            # feature.json is absent (#3024).
+            $candidate = Get-ChildItem -Path $specsDir -Filter 'plan.md' -File -Recurse -ErrorAction SilentlyContinue |
                 Sort-Object LastWriteTime -Descending |
                 Select-Object -First 1
             if ($candidate) {

extensions/catalog.community.json

@@ -1,6 +1,6 @@
 {
   "schema_version": "1.0",
-  "updated_at": "2026-07-07T00:00:00Z",
+  "updated_at": "2026-07-15T00:00:00Z",
   "catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json",
   "extensions": {
     "aide": {
@@ -809,8 +809,8 @@
       "id": "coding-standards-drift-control",
       "description": "Generate coding-standards drift reports and remediation tasks for active Spec Kit features",
       "author": "Igor Benicio de Mesquita",
-      "version": "0.3.1",
-      "download_url": "https://github.com/benizzio/spec-kit-coding-standards-drift-control/archive/refs/tags/v0.3.1.zip",
+      "version": "0.4.0",
+      "download_url": "https://github.com/benizzio/spec-kit-coding-standards-drift-control/archive/refs/tags/v0.4.0.zip",
       "repository": "https://github.com/benizzio/spec-kit-coding-standards-drift-control",
       "homepage": "https://github.com/benizzio/spec-kit-coding-standards-drift-control",
       "documentation": "https://github.com/benizzio/spec-kit-coding-standards-drift-control#readme",
@@ -835,7 +835,7 @@
       "downloads": 0,
       "stars": 0,
       "created_at": "2026-06-11T00:00:00Z",
-      "updated_at": "2026-06-11T00:00:00Z"
+      "updated_at": "2026-07-15T00:00:00Z"
     },
     "companion": {
       "name": "SpecKit Companion",
@@ -1106,10 +1106,10 @@
     "docguard": {
       "name": "DocGuard — CDD Enforcement",
       "id": "docguard",
-      "description": "The only doc-integrity engine with an MCP server, SARIF output, and a deterministic zero-LLM core. Validates, scores, and traces documentation against code — 24 validators, stable finding codes, GitHub Action with PR annotations, spec-kit hooks. Pure Node.js, one pinned dep.",
+      "description": "Doc-integrity engine with MCP server, SARIF output, and zero-LLM core. Validates, scores, and traces documentation against code — 24 validators, stable finding codes, spec-kit hooks. Pure Node.js.",
       "author": "raccioly",
-      "version": "0.30.0",
-      "download_url": "https://github.com/raccioly/docguard/releases/download/v0.30.0/spec-kit-docguard-v0.30.0.zip",
+      "version": "0.32.0",
+      "download_url": "https://github.com/raccioly/docguard/releases/download/v0.32.0/spec-kit-docguard-v0.32.0.zip",
       "repository": "https://github.com/raccioly/docguard",
       "homepage": "https://www.npmjs.com/package/docguard-cli",
       "documentation": "https://github.com/raccioly/docguard/blob/main/extensions/spec-kit-docguard/README.md",
@@ -1124,6 +1124,14 @@
             "name": "node",
             "version": ">=18.0.0",
             "required": true
+          },
+          {
+            "name": "npx",
+            "required": true
+          },
+          {
+            "name": "specify",
+            "required": false
           }
         ]
       },
@@ -1145,7 +1153,7 @@
       "downloads": 0,
       "stars": 0,
       "created_at": "2026-03-13T00:00:00Z",
-      "updated_at": "2026-07-06T00:00:00Z"
+      "updated_at": "2026-07-13T00:00:00Z"
     },
     "doctor": {
       "name": "Project Health Check",
@@ -1180,6 +1188,39 @@
       "created_at": "2026-03-13T00:00:00Z",
       "updated_at": "2026-03-13T00:00:00Z"
     },
+    "ears": {
+      "name": "EARS Requirements Syntax",
+      "id": "ears",
+      "description": "Author, lint, and convert requirements using EARS (Easy Approach to Requirements Syntax) - the five industry-standard sentence patterns for unambiguous, testable requirements.",
+      "author": "dhruv-15-03",
+      "version": "1.0.0",
+      "download_url": "https://github.com/dhruv-15-03/spec-kit-ears/archive/refs/tags/v1.0.0.zip",
+      "repository": "https://github.com/dhruv-15-03/spec-kit-ears",
+      "homepage": "https://github.com/dhruv-15-03/spec-kit-ears",
+      "documentation": "https://github.com/dhruv-15-03/spec-kit-ears/blob/main/README.md",
+      "changelog": "https://github.com/dhruv-15-03/spec-kit-ears/blob/main/CHANGELOG.md",
+      "license": "MIT",
+      "category": "docs",
+      "effect": "read-write",
+      "requires": {
+        "speckit_version": ">=0.9.0"
+      },
+      "provides": {
+        "commands": 3,
+        "hooks": 0
+      },
+      "tags": [
+        "ears",
+        "requirements",
+        "specification",
+        "quality"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-08T00:00:00Z",
+      "updated_at": "2026-07-08T00:00:00Z"
+    },
     "extensify": {
       "name": "Extensify",
       "id": "extensify",
@@ -1213,6 +1254,47 @@
       "created_at": "2026-03-18T00:00:00Z",
       "updated_at": "2026-04-23T00:00:00Z"
     },
+    "figma": {
+      "name": "Spec Kit Figma",
+      "id": "figma",
+      "description": "Agent-agnostic SpecKit extension that grounds spec, plan & task generation in Figma design context — REST + optional MCP, single/mono/multi-repo, macOS/Linux/Windows.",
+      "author": "Fyloss",
+      "version": "1.6.0",
+      "download_url": "https://github.com/Fyloss/spec-kit-figma/archive/refs/tags/v1.6.0.zip",
+      "repository": "https://github.com/Fyloss/spec-kit-figma",
+      "homepage": "https://github.com/Fyloss/spec-kit-figma",
+      "documentation": "https://github.com/Fyloss/spec-kit-figma/blob/main/docs/INSTALL.md",
+      "changelog": "https://github.com/Fyloss/spec-kit-figma/blob/main/CHANGELOG.md",
+      "license": "MIT",
+      "category": "integration",
+      "effect": "read-write",
+      "requires": {
+        "speckit_version": ">=0.1.0",
+        "tools": [
+          { "name": "git", "required": true },
+          { "name": "bash", "required": false },
+          { "name": "curl", "required": false },
+          { "name": "jq", "required": false },
+          { "name": "pwsh", "required": false }
+        ]
+      },
+      "provides": {
+        "commands": 5,
+        "hooks": 6
+      },
+      "tags": [
+        "figma",
+        "design",
+        "frontend",
+        "ui",
+        "design-system"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-08T00:00:00Z",
+      "updated_at": "2026-07-08T00:00:00Z"
+    },
     "fix-findings": {
       "name": "Fix Findings",
       "id": "fix-findings",
@@ -1353,6 +1435,57 @@
       "created_at": "2026-05-06T00:00:00Z",
       "updated_at": "2026-05-06T00:00:00Z"
     },
+    "gates": {
+      "name": "Quality Gates (Enforcement Layer)",
+      "id": "gates",
+      "description": "Deterministic quality enforcement for Spec Kit projects at three boundaries — agent hooks, git pre-commit, CI — with one policy file and provable enforcement (attestations, canaries, verified parity).",
+      "author": "schwichtgit",
+      "version": "0.1.0",
+      "download_url": "https://github.com/schwichtgit/spec-gates/releases/download/v0.1.0/gates-0.1.0.zip",
+      "repository": "https://github.com/schwichtgit/spec-gates",
+      "homepage": "https://github.com/schwichtgit/spec-gates",
+      "documentation": "https://github.com/schwichtgit/spec-gates/blob/main/docs/how-it-works.md",
+      "license": "MIT",
+      "category": "process",
+      "effect": "read-write",
+      "requires": {
+        "speckit_version": ">=0.12.0",
+        "tools": [
+          {
+            "name": "jq",
+            "required": true
+          },
+          {
+            "name": "git",
+            "required": true
+          },
+          {
+            "name": "node",
+            "required": false
+          },
+          {
+            "name": "shellcheck",
+            "required": false
+          }
+        ]
+      },
+      "provides": {
+        "commands": 5,
+        "hooks": 1
+      },
+      "tags": [
+        "quality",
+        "enforcement",
+        "hooks",
+        "ci",
+        "governance"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-09T00:00:00Z",
+      "updated_at": "2026-07-13T00:00:00Z"
+    },
     "github-issues": {
       "name": "GitHub Issues Integration 1",
       "id": "github-issues",
@@ -2143,6 +2276,42 @@
       "created_at": "2026-05-08T00:00:00Z",
       "updated_at": "2026-05-08T00:00:00Z"
     },
+    "memory": {
+      "name": "Spec Kit Memory",
+      "id": "memory",
+      "description": "Recalls prior specs and decisions from configurable memory tools (e.g. memsearch) before SDLC stages, so planning and specification start from what the project already knows.",
+      "author": "Andrey Zaytsev",
+      "version": "0.3.0",
+      "download_url": "https://github.com/zaytsevand/spec-kit-memory/archive/refs/tags/v0.3.0.zip",
+      "repository": "https://github.com/zaytsevand/spec-kit-memory",
+      "homepage": "https://github.com/zaytsevand/spec-kit-memory",
+      "documentation": "https://github.com/zaytsevand/spec-kit-memory/blob/main/README.md",
+      "changelog": "",
+      "license": "MIT",
+      "category": "docs",
+      "effect": "read-write",
+      "requires": {
+        "speckit_version": ">=0.2.0",
+        "tools": [
+          { "name": "memsearch", "required": false }
+        ]
+      },
+      "provides": {
+        "commands": 2,
+        "hooks": 3
+      },
+      "tags": [
+        "memory",
+        "recall",
+        "research",
+        "memsearch"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-10T00:00:00Z",
+      "updated_at": "2026-07-10T00:00:00Z"
+    },
     "memory-loader": {
       "name": "Memory Loader",
       "id": "memory-loader",
@@ -2297,6 +2466,48 @@
       "created_at": "2026-05-04T02:51:52Z",
       "updated_at": "2026-06-18T00:00:00Z"
     },
+    "multi-repo-sync": {
+      "name": "Multi-Repo Branch Sync",
+      "id": "multi-repo-sync",
+      "description": "Creates the feature branch in affected sub-repositories and git submodules via plan/tasks hooks",
+      "author": "Fyloss",
+      "version": "1.0.0",
+      "download_url": "https://github.com/fyloss/spec-kit-multi-repo-sync/releases/download/v1.0.0/spec-kit-multi-repo-sync.zip",
+      "sha256": "12a5c7392145b4424b20715aaa3d8b6a8218c143dea596873e344146c1a76ba0",
+      "repository": "https://github.com/fyloss/spec-kit-multi-repo-sync",
+      "homepage": "https://github.com/fyloss/spec-kit-multi-repo-sync",
+      "documentation": "https://github.com/fyloss/spec-kit-multi-repo-sync/blob/main/README.md",
+      "changelog": "https://github.com/fyloss/spec-kit-multi-repo-sync/blob/main/CHANGELOG.md",
+      "license": "MIT",
+      "category": "process",
+      "effect": "read-write",
+      "requires": {
+        "speckit_version": ">=0.2.0",
+        "tools": [
+          {
+            "name": "git",
+            "version": ">=2.31",
+            "required": true
+          }
+        ]
+      },
+      "provides": {
+        "commands": 3,
+        "hooks": 2
+      },
+      "tags": [
+        "git",
+        "branching",
+        "multi-repo",
+        "submodules",
+        "workflow"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-13T00:00:00Z",
+      "updated_at": "2026-07-13T00:00:00Z"
+    },
     "multi-sites": {
       "name": "Multi-Sites Spec Kit",
       "id": "multi-sites",
@@ -2466,6 +2677,46 @@
       "created_at": "2026-04-24T14:00:00Z",
       "updated_at": "2026-04-24T14:00:00Z"
     },
+    "patchwarden-evidence": {
+      "name": "PatchWarden Evidence Pack",
+      "id": "patchwarden-evidence",
+      "description": "Map Spec Kit tasks into a guarded PatchWarden Goal and export bounded, traceable evidence for an accepted lineage.",
+      "author": "Zengjie",
+      "version": "1.0.1",
+      "download_url": "https://github.com/jiezeng2004-design/spec-kit-patchwarden/archive/refs/tags/v1.0.1.zip",
+      "repository": "https://github.com/jiezeng2004-design/spec-kit-patchwarden",
+      "homepage": "https://github.com/jiezeng2004-design/spec-kit-patchwarden",
+      "documentation": "https://github.com/jiezeng2004-design/spec-kit-patchwarden/blob/main/README.md",
+      "changelog": "https://github.com/jiezeng2004-design/spec-kit-patchwarden/blob/main/CHANGELOG.md",
+      "license": "MIT",
+      "category": "process",
+      "effect": "read-write",
+      "requires": {
+        "speckit_version": ">=0.1.0",
+        "tools": [
+          {
+            "name": "patchwarden",
+            "version": ">=1.5.1",
+            "required": true
+          }
+        ]
+      },
+      "provides": {
+        "commands": 2,
+        "hooks": 2
+      },
+      "tags": [
+        "verification",
+        "evidence",
+        "traceability",
+        "security"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-14T00:00:00Z",
+      "updated_at": "2026-07-14T00:00:00Z"
+    },
     "plan-review-gate": {
       "name": "Plan Review Gate",
       "id": "plan-review-gate",
@@ -4282,6 +4533,40 @@
       "created_at": "2026-03-03T00:00:00Z",
       "updated_at": "2026-04-09T00:00:00Z"
     },
+    "verify-review-ship": {
+      "name": "Verify Review Ship",
+      "id": "verify-review-ship",
+      "description": "Adds post-implementation verify, review, and ship readiness gates to Spec Kit workflows.",
+      "author": "Carlos Eduardo Gevaerd Araujo",
+      "version": "0.1.0",
+      "download_url": "https://github.com/cadugevaerd/spec-kit-verify-review-ship/archive/refs/tags/v0.1.0.zip",
+      "repository": "https://github.com/cadugevaerd/spec-kit-verify-review-ship",
+      "homepage": "https://github.com/cadugevaerd/spec-kit-verify-review-ship",
+      "documentation": "https://github.com/cadugevaerd/spec-kit-verify-review-ship/blob/main/README.md",
+      "changelog": "https://github.com/cadugevaerd/spec-kit-verify-review-ship/blob/main/CHANGELOG.md",
+      "license": "MIT",
+      "category": "process",
+      "effect": "read-only",
+      "requires": {
+        "speckit_version": ">=0.1.0"
+      },
+      "provides": {
+        "commands": 3,
+        "hooks": 1
+      },
+      "tags": [
+        "quality",
+        "review",
+        "shipping",
+        "workflow",
+        "testing"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-10T00:00:00Z",
+      "updated_at": "2026-07-10T00:00:00Z"
+    },
     "verify-tasks": {
       "name": "Verify Tasks Extension",
       "id": "verify-tasks",

extensions/catalog.json

@@ -48,4 +48,4 @@
       ]
     }
   }
-}
+}

extensions/git/scripts/python/auto_commit.py

@@ -0,0 +1,187 @@
+#!/usr/bin/env python3
+"""Git extension: auto_commit.py
+
+Automatically commit changes after a Spec Kit command completes.
+Python port of ``auto-commit.sh`` / ``auto-commit.ps1``.
+Checks per-command config keys in git-config.yml before committing.
+
+Usage: auto_commit.py <event_name>
+  e.g.: auto_commit.py after_specify
+"""
+
+from __future__ import annotations
+
+import re
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+
+
+def _find_project_root(start: Path) -> Path | None:
+    current = start
+    while True:
+        if (current / ".specify").is_dir() or (current / ".git").exists():
+            return current
+        if current.parent == current:
+            return None
+        current = current.parent
+
+
+def _value_after_colon(line: str) -> str:
+    return re.sub(r"^[^:]*:\s*", "", line)
+
+
+def _strip_quotes(value: str) -> str:
+    """Strip one leading quote and all trailing quotes, mirroring the bash sed."""
+    value = re.sub(r"^[\"']", "", value)
+    return re.sub(r"[\"']*$", "", value)
+
+
+def _parse_auto_commit_config(
+    config_file: Path, event_name: str
+) -> tuple[bool, str]:
+    """Parse the auto_commit section for this event, mirroring the bash line parser.
+
+    Returns (enabled, commit_msg). Looks for auto_commit.<event_name>.enabled
+    and .message, with auto_commit.default as fallback.
+    """
+    enabled = False
+    commit_msg = ""
+    default_enabled = False
+    in_auto_commit = False
+    in_event = False
+
+    try:
+        content = config_file.read_text(encoding="utf-8")
+    except (OSError, UnicodeDecodeError):
+        # Unreadable or non-UTF-8 config is treated like a missing one:
+        # auto-commit stays disabled instead of crashing with a traceback.
+        return False, ""
+    for record in content.splitlines(keepends=True):
+        if not record.endswith("\n"):
+            break
+        line = record[:-1]
+        if line.startswith("auto_commit:"):
+            in_auto_commit = True
+            in_event = False
+            continue
+
+        # Exit auto_commit section on next top-level key
+        if in_auto_commit and re.match(r"^[a-z]", line):
+            break
+
+        if not in_auto_commit:
+            continue
+
+        if re.match(r"^\s+default:\s", line):
+            value = re.sub(r"\s", "", _value_after_colon(line)).lower()
+            if value == "true":
+                default_enabled = True
+
+        if re.match(rf"^\s+{re.escape(event_name)}:", line):
+            in_event = True
+            continue
+
+        if in_event:
+            # Exit on next sibling key (same indent level as event name)
+            if re.match(r"^\s{2}[a-z]", line) and not re.match(r"^\s{4}", line):
+                in_event = False
+                continue
+            if re.search(r"\s+enabled:", line):
+                value = re.sub(r"\s", "", _value_after_colon(line)).lower()
+                if value == "true":
+                    enabled = True
+                elif value == "false":
+                    enabled = False
+            if re.search(r"\s+message:", line):
+                commit_msg = _strip_quotes(_value_after_colon(line))
+
+    # If event-specific key not found, use default — but only if the event
+    # section didn't exist at all (an explicit false must win).
+    if not enabled and default_enabled:
+        if not re.search(rf"^\s*{re.escape(event_name)}:", content, re.MULTILINE):
+            enabled = True
+
+    return enabled, commit_msg
+
+
+def main(argv: list[str]) -> int:
+    event_name = argv[0] if argv else ""
+    if not event_name:
+        print(f"Usage: {Path(sys.argv[0]).name} <event_name>", file=sys.stderr)
+        return 1
+
+    script_dir = Path(__file__).resolve().parent
+    repo_root = _find_project_root(script_dir) or Path.cwd()
+
+    if shutil.which("git") is None:
+        print("[specify] Warning: Git not found; skipped auto-commit", file=sys.stderr)
+        return 0
+
+    probe = subprocess.run(
+        ["git", "rev-parse", "--is-inside-work-tree"],
+        cwd=repo_root,
+        capture_output=True,
+        text=True,
+    )
+    if probe.returncode != 0:
+        print(
+            "[specify] Warning: Not a Git repository; skipped auto-commit",
+            file=sys.stderr,
+        )
+        return 0
+
+    config_file = repo_root / ".specify" / "extensions" / "git" / "git-config.yml"
+    if not config_file.is_file():
+        # No config file — auto-commit disabled by default
+        return 0
+
+    enabled, commit_msg = _parse_auto_commit_config(config_file, event_name)
+    if not enabled:
+        return 0
+
+    # Check if there are changes to commit
+    def _quiet(*args: str) -> bool:
+        return (
+            subprocess.run(
+                ["git", *args], cwd=repo_root, capture_output=True, text=True
+            ).returncode
+            == 0
+        )
+
+    untracked = subprocess.run(
+        ["git", "ls-files", "--others", "--exclude-standard"],
+        cwd=repo_root,
+        capture_output=True,
+        text=True,
+    ).stdout.strip()
+    if _quiet("diff", "--quiet", "HEAD") and _quiet("diff", "--cached", "--quiet") and not untracked:
+        print(f"[specify] No changes to commit after {event_name}", file=sys.stderr)
+        return 0
+
+    # Derive a human-readable command name from the event
+    # e.g., after_specify -> specify, before_plan -> plan
+    command_name = re.sub(r"^(after_|before_)", "", event_name)
+    phase = "before" if event_name.startswith("before_") else "after"
+
+    if not commit_msg:
+        commit_msg = f"[Spec Kit] Auto-commit {phase} {command_name}"
+
+    steps = [
+        (["git", "add", "."], "git add"),
+        (["git", "commit", "-q", "-m", commit_msg], "git commit"),
+    ]
+    for cmd, label in steps:
+        result = subprocess.run(cmd, cwd=repo_root, capture_output=True, text=True)
+        if result.returncode != 0:
+            output = (result.stdout + result.stderr).strip()
+            print(f"[specify] Error: {label} failed: {output}", file=sys.stderr)
+            return 1
+
+    print(f"[OK] Changes committed {phase} {command_name}", file=sys.stderr)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main(sys.argv[1:]))

extensions/git/scripts/python/create_new_feature_branch.py

@@ -0,0 +1,634 @@
+#!/usr/bin/env python3
+"""Git extension: create_new_feature_branch.py
+
+Creates a git feature branch only. The feature directory and spec file are
+created by the core create-new-feature script. Python port of
+``create-new-feature-branch.sh`` / ``create-new-feature-branch.ps1``.
+
+Loads the core Python helpers from the project's installed scripts when
+available, falling back to the minimal git helpers next to this script.
+"""
+
+from __future__ import annotations
+
+import importlib.util
+import json
+import os
+import re
+import shutil
+import subprocess
+import sys
+from dataclasses import dataclass, field
+from datetime import datetime
+from pathlib import Path
+
+SCRIPT_DIR = Path(__file__).resolve().parent
+MAX_BRANCH_LENGTH = 244  # GitHub enforces a 244-byte limit on branch names
+
+USAGE = (
+    "Usage: create_new_feature_branch.py [--json] [--dry-run] "
+    "[--allow-existing-branch] [--short-name <name>] [--number N] "
+    "[--timestamp] <feature_description>"
+)
+
+HELP_TEXT = f"""{USAGE}
+
+Options:
+  --json              Output in JSON format
+  --dry-run           Compute branch name without creating the branch
+  --allow-existing-branch  Switch to branch if it already exists instead of failing
+  --short-name <name> Provide a custom short name (2-4 words) for the branch
+  --number N          Specify branch number manually (overrides auto-detection)
+  --timestamp         Use timestamp prefix (YYYYMMDD-HHMMSS) instead of sequential numbering
+  --help, -h          Show this help message
+
+Environment variables:
+  GIT_BRANCH_NAME     Use this exact branch name, bypassing all prefix/suffix generation
+
+Configuration:
+  branch_template     Optional git-config.yml template with {{author}}, {{app}}, {{number}}, {{slug}}
+  branch_prefix       Optional shorthand namespace expanded before {{number}}-{{slug}}
+
+Examples:
+  create_new_feature_branch.py 'Add user authentication system' --short-name 'user-auth'
+  create_new_feature_branch.py 'Implement OAuth2 integration for API' --number 5
+  create_new_feature_branch.py --timestamp --short-name 'user-auth' 'Add user authentication'
+  GIT_BRANCH_NAME=my-branch create_new_feature_branch.py 'feature description'
+"""
+
+STOP_WORDS = frozenset(
+    "i a an the to for of in on at by with from is are was were be been being "
+    "have has had do does did will would should could can may might must shall "
+    "this that these those my your our their want need add get set".split()
+)
+
+
+def _err(message: str) -> None:
+    print(message, file=sys.stderr)
+
+
+def _persist_hint(var_name: str, value: str) -> str:
+    """Shell-appropriate guidance for persisting an env var in the caller's shell."""
+    if os.name == "nt":
+        escaped_value = value.replace("'", "''")
+        return f"$env:{var_name} = '{escaped_value}'"
+    escaped_value = re.sub(r"([^\w@%+=:,./-])", r"\\\1", value)
+    return f"export {var_name}={escaped_value}"
+
+
+@dataclass
+class Args:
+    json_mode: bool = False
+    dry_run: bool = False
+    allow_existing: bool = False
+    short_name: str = ""
+    branch_number: str = ""
+    use_timestamp: bool = False
+    description_parts: list[str] = field(default_factory=list)
+
+
+def parse_args(argv: list[str]) -> Args:
+    args = Args()
+    i = 0
+    while i < len(argv):
+        arg = argv[i]
+        if arg == "--json":
+            args.json_mode = True
+        elif arg == "--dry-run":
+            args.dry_run = True
+        elif arg == "--allow-existing-branch":
+            args.allow_existing = True
+        elif arg == "--short-name":
+            if i + 1 >= len(argv) or argv[i + 1].startswith("--"):
+                _err("Error: --short-name requires a value")
+                raise SystemExit(1)
+            i += 1
+            args.short_name = argv[i]
+        elif arg == "--number":
+            if i + 1 >= len(argv) or argv[i + 1].startswith("--"):
+                _err("Error: --number requires a value")
+                raise SystemExit(1)
+            i += 1
+            args.branch_number = argv[i]
+            if not re.fullmatch(r"[0-9]+", args.branch_number):
+                _err("Error: --number must be a non-negative integer")
+                raise SystemExit(1)
+        elif arg == "--timestamp":
+            args.use_timestamp = True
+        elif arg in ("--help", "-h"):
+            print(HELP_TEXT)
+            raise SystemExit(0)
+        else:
+            args.description_parts.append(arg)
+        i += 1
+    return args
+
+
+# ── Core helpers loading ─────────────────────────────────────────────────────
+
+
+def _find_project_root(start: Path) -> Path | None:
+    current = start
+    while True:
+        if (current / ".specify").is_dir() or (current / ".git").exists():
+            return current
+        if current.parent == current:
+            return None
+        current = current.parent
+
+
+def _load_core_common(project_root: Path | None):
+    """Load the core common.py from the project's installed scripts.
+
+    Search locations in priority order, mirroring the bash script:
+     1. .specify/scripts/python/common.py (installed project)
+     2. scripts/python/common.py (source checkout fallback)
+    Returns the loaded module or None.
+    """
+    if project_root is None:
+        return None
+    for relative in (".specify/scripts/python/common.py", "scripts/python/common.py"):
+        candidate = project_root / relative
+        if candidate.is_file():
+            spec = importlib.util.spec_from_file_location("speckit_core_common", candidate)
+            if spec is None or spec.loader is None:
+                continue
+            module = importlib.util.module_from_spec(spec)
+            sys.modules[spec.name] = module
+            spec.loader.exec_module(module)
+            return module
+    return None
+
+
+def _local_has_git(repo_root: Path) -> bool:
+    git_marker = repo_root / ".git"
+    if not (git_marker.is_dir() or git_marker.is_file()):
+        return False
+    if shutil.which("git") is None:
+        return False
+    return (
+        subprocess.run(
+            ["git", "-C", str(repo_root), "rev-parse", "--is-inside-work-tree"],
+            capture_output=True,
+            text=True,
+        ).returncode
+        == 0
+    )
+
+
+# ── Numbering ────────────────────────────────────────────────────────────────
+
+
+def get_highest_from_specs(specs_dir: Path) -> int:
+    highest = 0
+    if specs_dir.is_dir():
+        for entry in specs_dir.iterdir():
+            if not entry.is_dir():
+                continue
+            name = entry.name
+            # Match sequential prefixes (>=3 digits), but skip timestamp dirs.
+            if re.match(r"^[0-9]{3,}-", name) and not re.match(
+                r"^[0-9]{8}-[0-9]{6}-", name
+            ):
+                number = int(re.match(r"^[0-9]+", name).group(0))
+                highest = max(highest, number)
+    return highest
+
+
+def _extract_highest_number(names: list[str], scope_prefix: str) -> int:
+    """Extract the highest sequential feature number from a list of ref names."""
+    highest = 0
+    for name in names:
+        if not name:
+            continue
+        if scope_prefix:
+            if not name.startswith(scope_prefix):
+                continue
+            name = name[len(scope_prefix) :]
+        name = name.rsplit("/", 1)[-1]
+        if (
+            re.match(r"^[0-9]{3,}-", name)
+            and not re.match(r"^[0-9]{8}-[0-9]{6}-", name)
+            and not re.match(r"^[0-9]{7}-[0-9]{6}-", name)
+            and not re.fullmatch(r"[0-9]{7,8}-[0-9]{6}", name)
+        ):
+            match = re.match(r"^([0-9]{3,})-", name)
+            number = int(match.group(1)) if match else 0
+            highest = max(highest, number)
+    return highest
+
+
+def _git_lines(repo_root: Path, *args: str, env_extra: dict | None = None) -> list[str]:
+    if shutil.which("git") is None:
+        return []
+    env = {**os.environ, **(env_extra or {})}
+    result = subprocess.run(
+        ["git", *args], cwd=repo_root, capture_output=True, text=True, env=env
+    )
+    if result.returncode != 0:
+        return []
+    return result.stdout.splitlines()
+
+
+def get_highest_from_branches(repo_root: Path, scope_prefix: str) -> int:
+    names = []
+    for line in _git_lines(repo_root, "branch", "-a"):
+        line = re.sub(r"^[+*]\s+", "", line)
+        line = line.lstrip()
+        line = re.sub(r"^remotes/[^/]*/", "", line)
+        names.append(line)
+    return _extract_highest_number(names, scope_prefix)
+
+
+def get_highest_from_remote_refs(repo_root: Path, scope_prefix: str) -> int:
+    """Highest number from remote branches without fetching (side-effect-free)."""
+    highest = 0
+    for remote in _git_lines(repo_root, "remote"):
+        refs = _git_lines(
+            repo_root,
+            "ls-remote",
+            "--heads",
+            remote,
+            env_extra={"GIT_TERMINAL_PROMPT": "0"},
+        )
+        names = [re.sub(r".*refs/heads/", "", ref) for ref in refs]
+        highest = max(highest, _extract_highest_number(names, scope_prefix))
+    return highest
+
+
+def check_existing_branches(
+    repo_root: Path, specs_dir: Path, skip_fetch: bool, scope_prefix: str
+) -> int:
+    """Check existing branches and return the next available number."""
+    if skip_fetch:
+        highest_branch = max(
+            get_highest_from_remote_refs(repo_root, scope_prefix),
+            get_highest_from_branches(repo_root, scope_prefix),
+        )
+    else:
+        subprocess.run(
+            ["git", "fetch", "--all", "--prune"],
+            cwd=repo_root,
+            capture_output=True,
+            text=True,
+        )
+        highest_branch = get_highest_from_branches(repo_root, scope_prefix)
+
+    return max(highest_branch, get_highest_from_specs(specs_dir)) + 1
+
+
+# ── Branch naming ────────────────────────────────────────────────────────────
+
+
+def clean_branch_name(name: str) -> str:
+    name = re.sub(r"[^a-z0-9]", "-", name.lower())
+    name = re.sub(r"-+", "-", name)
+    return name.strip("-")
+
+
+def generate_branch_name(description: str) -> str:
+    """Generate a branch suffix from the description with stop word filtering."""
+    clean_name = re.sub(r"[^a-z0-9]", " ", description.lower())
+
+    meaningful_words = []
+    for word in clean_name.split():
+        if word in STOP_WORDS:
+            continue
+        if len(word) >= 3:
+            meaningful_words.append(word)
+        # Keep short words only when they appear uppercased in the original
+        # description (acronyms like "API" or "DB").
+        elif re.search(rf"\b{re.escape(word.upper())}\b", description):
+            meaningful_words.append(word)
+
+    if meaningful_words:
+        max_words = 4 if len(meaningful_words) == 4 else 3
+        return "-".join(meaningful_words[:max_words])
+
+    cleaned = clean_branch_name(description)
+    return "-".join([part for part in cleaned.split("-") if part][:3])
+
+
+def branch_token(value: str, fallback: str) -> str:
+    cleaned = clean_branch_name(value)
+    return cleaned if cleaned else fallback
+
+
+def get_author_token(repo_root: Path) -> str:
+    author = ""
+    if shutil.which("git") is not None:
+        lines = _git_lines(repo_root, "config", "user.name")
+        author = lines[0] if lines else ""
+        if not author:
+            lines = _git_lines(repo_root, "config", "user.email")
+            email = lines[0] if lines else ""
+            author = email.split("@")[0]
+    if not author:
+        author = os.environ.get("USER") or os.environ.get("USERNAME") or "unknown"
+    return branch_token(author, "unknown")
+
+
+def get_app_token(repo_root: Path) -> str:
+    return branch_token(repo_root.name, "app")
+
+
+def read_git_config_value(config_file: Path, key: str) -> str:
+    if not config_file.is_file():
+        return ""
+    try:
+        lines = config_file.read_text(encoding="utf-8").splitlines()
+    except (OSError, UnicodeDecodeError):
+        return ""
+    for line in lines:
+        if re.match(rf"^\s*{re.escape(key)}:", line):
+            value = re.sub(rf"^\s*{re.escape(key)}:\s*", "", line)
+            value = re.sub(r"\s+#.*$", "", value)
+            value = value.strip()
+            value = re.sub(r'^"|"$', "", value)
+            value = re.sub(r"^'|'$", "", value)
+            return value
+    return ""
+
+
+def resolve_branch_template(config_file: Path) -> str:
+    template = read_git_config_value(config_file, "branch_template")
+    if template:
+        return template
+
+    prefix = read_git_config_value(config_file, "branch_prefix")
+    if not prefix:
+        return ""
+    if prefix.endswith("/"):
+        return f"{prefix}{{number}}-{{slug}}"
+    return f"{prefix}/{{number}}-{{slug}}"
+
+
+def validate_branch_template(template: str) -> None:
+    if not template:
+        return
+    if "{number}" not in template:
+        _err(
+            "Error: branch_template must include the {number} token so generated "
+            "branches remain valid feature branches."
+        )
+        raise SystemExit(1)
+    slug_index = template.find("{slug}")
+    if slug_index != -1 and "{number}" in template[slug_index:]:
+        _err(
+            "Error: branch_template must not place {slug} before {number}; "
+            "use {slug} only in the final feature segment."
+        )
+        raise SystemExit(1)
+    feature_segment = template.rsplit("/", 1)[-1]
+    if not feature_segment.startswith("{number}-"):
+        _err(
+            "Error: branch_template must put {number}- at the start of the final "
+            "path segment so generated branches remain valid feature branches."
+        )
+        raise SystemExit(1)
+
+
+def render_branch_template(
+    template: str, feature_num: str, branch_suffix: str, author_token: str, app_token: str
+) -> str:
+    rendered = template
+    rendered = rendered.replace("{author}", author_token)
+    rendered = rendered.replace("{app}", app_token)
+    rendered = rendered.replace("{number}", feature_num)
+    rendered = rendered.replace("{slug}", branch_suffix)
+    return rendered
+
+
+def extract_feature_num_from_branch(branch_name: str) -> str:
+    feature_segment = branch_name.rsplit("/", 1)[-1]
+    match = re.match(r"^[0-9]{8}-[0-9]{6}-", feature_segment)
+    if match:
+        return match.group(0).rstrip("-")
+    match = re.match(r"^[0-9]+-", feature_segment)
+    if match:
+        return match.group(0).rstrip("-")
+    return branch_name
+
+
+def _byte_length(value: str) -> int:
+    return len(value.encode("utf-8"))
+
+
+# ── Main ─────────────────────────────────────────────────────────────────────
+
+
+def main(argv: list[str]) -> int:
+    args = parse_args(argv)
+
+    feature_description = " ".join(args.description_parts)
+    if not feature_description:
+        _err(USAGE)
+        return 1
+    feature_description = feature_description.strip()
+    if not feature_description:
+        _err("Error: Feature description cannot be empty or contain only whitespace")
+        return 1
+
+    project_root = _find_project_root(SCRIPT_DIR)
+    core = _load_core_common(project_root)
+
+    # SPECIFY_INIT_DIR is resolved (and validated) by the core resolver. If the
+    # core helpers were not found, refuse rather than silently falling back to
+    # the wrong root.
+    if os.environ.get("SPECIFY_INIT_DIR") and (
+        core is None or not hasattr(core, "resolve_specify_init_dir")
+    ):
+        _err(
+            "Error: SPECIFY_INIT_DIR requires updated Spec Kit core scripts "
+            "(common.py with resolve_specify_init_dir), which were not found."
+        )
+        return 1
+
+    if core is not None and hasattr(core, "get_repo_root"):
+        # Pass script path so cwd-outside-repo callers land on the same
+        # fallback the bash twin does. Older cores don't accept the kwarg —
+        # fall back to the no-arg call for compatibility.
+        try:
+            repo_root = core.get_repo_root(script_file=Path(__file__))
+        except TypeError:
+            repo_root = core.get_repo_root()
+    else:
+        toplevel = _git_lines(Path.cwd(), "rev-parse", "--show-toplevel")
+        if toplevel:
+            repo_root = Path(toplevel[0])
+        elif project_root is not None:
+            repo_root = project_root
+        else:
+            _err("Error: Could not determine repository root.")
+            return 1
+    repo_root = Path(repo_root)
+
+    has_git_repo = _local_has_git(repo_root)
+
+    specs_dir = repo_root / "specs"
+    config_file = repo_root / ".specify" / "extensions" / "git" / "git-config.yml"
+
+    author_token = get_author_token(repo_root)
+    app_token = get_app_token(repo_root)
+    branch_template = resolve_branch_template(config_file)
+    validate_branch_template(branch_template)
+
+    def build_branch_name(feature_num: str, branch_suffix: str) -> str:
+        if branch_template:
+            return render_branch_template(
+                branch_template, feature_num, branch_suffix, author_token, app_token
+            )
+        return f"{feature_num}-{branch_suffix}"
+
+    branch_number = args.branch_number
+
+    # Check for GIT_BRANCH_NAME env var override (exact name, no prefix/suffix)
+    env_branch_name = os.environ.get("GIT_BRANCH_NAME", "")
+    if env_branch_name:
+        branch_name = env_branch_name
+        feature_num = extract_feature_num_from_branch(branch_name)
+        branch_suffix = branch_name
+    else:
+        if args.short_name:
+            branch_suffix = clean_branch_name(args.short_name)
+        else:
+            branch_suffix = generate_branch_name(feature_description)
+
+        if args.use_timestamp and branch_number:
+            _err("[specify] Warning: --number is ignored when --timestamp is used")
+            branch_number = ""
+
+        if args.use_timestamp:
+            feature_num = datetime.now().strftime("%Y%m%d-%H%M%S")
+            branch_name = build_branch_name(feature_num, branch_suffix)
+        else:
+            scope_prefix = ""
+            if branch_template:
+                prefix_template = branch_template.split("{number}")[0]
+                scope_prefix = render_branch_template(
+                    prefix_template, "", branch_suffix, author_token, app_token
+                )
+            if not branch_number:
+                if args.dry_run and has_git_repo:
+                    branch_number = check_existing_branches(
+                        repo_root, specs_dir, True, scope_prefix
+                    )
+                elif args.dry_run:
+                    branch_number = get_highest_from_specs(specs_dir) + 1
+                elif has_git_repo:
+                    branch_number = check_existing_branches(
+                        repo_root, specs_dir, False, scope_prefix
+                    )
+                else:
+                    branch_number = get_highest_from_specs(specs_dir) + 1
+
+            feature_num = f"{int(branch_number):03d}"
+            branch_name = build_branch_name(feature_num, branch_suffix)
+
+    branch_byte_len = _byte_length(branch_name)
+    if env_branch_name and branch_byte_len > MAX_BRANCH_LENGTH:
+        _err(
+            "Error: GIT_BRANCH_NAME must be 244 bytes or fewer in UTF-8. "
+            f"Provided value is {branch_byte_len} bytes."
+        )
+        return 1
+    if branch_byte_len > MAX_BRANCH_LENGTH:
+        original_branch_name = branch_name
+        truncated_suffix = branch_suffix
+        while _byte_length(branch_name) > MAX_BRANCH_LENGTH and truncated_suffix:
+            truncated_suffix = truncated_suffix[:-1]
+            truncated_suffix = truncated_suffix.rstrip("-")
+            branch_name = build_branch_name(feature_num, truncated_suffix)
+        if _byte_length(branch_name) > MAX_BRANCH_LENGTH:
+            _err("Error: Branch template prefix exceeds GitHub's 244-byte branch name limit.")
+            return 1
+
+        _err("[specify] Warning: Branch name exceeded GitHub's 244-byte limit")
+        _err(
+            f"[specify] Original: {original_branch_name} "
+            f"({_byte_length(original_branch_name)} bytes)"
+        )
+        _err(f"[specify] Truncated to: {branch_name} ({_byte_length(branch_name)} bytes)")
+
+    if not args.dry_run:
+        if has_git_repo:
+            create = subprocess.run(
+                ["git", "checkout", "-q", "-b", branch_name],
+                cwd=repo_root,
+                capture_output=True,
+                text=True,
+            )
+            if create.returncode != 0:
+                current_branch_lines = _git_lines(
+                    repo_root, "rev-parse", "--abbrev-ref", "HEAD"
+                )
+                current_branch = current_branch_lines[0] if current_branch_lines else ""
+                branch_exists = bool(
+                    _git_lines(repo_root, "branch", "--list", branch_name)
+                )
+                if branch_exists:
+                    if args.allow_existing:
+                        if current_branch != branch_name:
+                            switch = subprocess.run(
+                                ["git", "checkout", "-q", branch_name],
+                                cwd=repo_root,
+                                capture_output=True,
+                                text=True,
+                            )
+                            if switch.returncode != 0:
+                                _err(
+                                    f"Error: Failed to switch to existing branch '{branch_name}'. "
+                                    "Please resolve any local changes or conflicts and try again."
+                                )
+                                if switch.stderr.strip():
+                                    _err(switch.stderr.strip())
+                                return 1
+                    elif args.use_timestamp:
+                        _err(
+                            f"Error: Branch '{branch_name}' already exists. Rerun to get "
+                            "a new timestamp or use a different --short-name."
+                        )
+                        return 1
+                    else:
+                        _err(
+                            f"Error: Branch '{branch_name}' already exists. Please use a "
+                            "different feature name or specify a different number with --number."
+                        )
+                        return 1
+                else:
+                    _err(f"Error: Failed to create git branch '{branch_name}'.")
+                    if create.stderr.strip():
+                        _err(create.stderr.strip())
+                    else:
+                        _err("Please check your git configuration and try again.")
+                    return 1
+        else:
+            _err(
+                "[specify] Warning: Git repository not detected; skipped branch "
+                f"creation for {branch_name}"
+            )
+
+        _err(f"# To persist: {_persist_hint('SPECIFY_FEATURE', branch_name)}")
+
+    if args.json_mode:
+        payload: dict[str, object] = {
+            "BRANCH_NAME": branch_name,
+            "FEATURE_NUM": feature_num,
+        }
+        if args.dry_run:
+            payload["DRY_RUN"] = True
+        print(json.dumps(payload, ensure_ascii=False, separators=(",", ":")))
+    else:
+        print(f"BRANCH_NAME: {branch_name}")
+        print(f"FEATURE_NUM: {feature_num}")
+        if not args.dry_run:
+            print(
+                "# To persist in your shell: "
+                f"{_persist_hint('SPECIFY_FEATURE', branch_name)}"
+            )
+
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main(sys.argv[1:]))

extensions/git/scripts/python/git_common.py

@@ -0,0 +1,81 @@
+#!/usr/bin/env python3
+"""Git-specific common helpers for the git extension.
+
+Python port of ``git-common.sh`` / ``git-common.ps1`` — contains only
+git-specific branch validation and detection logic.
+"""
+
+from __future__ import annotations
+
+import re
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+
+
+def has_git(repo_root: Path | None = None) -> bool:
+    """Check if we have git available at the repo root."""
+    root = Path(repo_root) if repo_root is not None else Path.cwd()
+    git_marker = root / ".git"
+    if not (git_marker.is_dir() or git_marker.is_file()):
+        return False
+    if shutil.which("git") is None:
+        return False
+    result = subprocess.run(
+        ["git", "-C", str(root), "rev-parse", "--is-inside-work-tree"],
+        capture_output=True,
+        text=True,
+    )
+    return result.returncode == 0
+
+
+def effective_branch_name(raw: str) -> str:
+    """Strip a single optional path segment (e.g. gitflow "feat/004-name" -> "004-name").
+
+    Only when the full name is exactly two slash-free segments; otherwise
+    returns the raw name.
+    """
+    match = re.fullmatch(r"([^/]+)/([^/]+)", raw)
+    if match:
+        return match.group(2)
+    return raw
+
+
+def check_feature_branch(raw: str, has_git_repo: bool) -> bool:
+    """Validate that a branch name matches the expected feature branch pattern.
+
+    Accepts sequential (###-* with >=3 digits) or timestamp (YYYYMMDD-HHMMSS-*)
+    formats, either at the start of the branch or after path-style namespace
+    prefixes. Logic aligned with the bash/PowerShell twins.
+    """
+    if not has_git_repo:
+        print(
+            "[specify] Warning: Git repository not detected; skipped branch validation",
+            file=sys.stderr,
+        )
+        return True
+
+    branch = effective_branch_name(raw)
+    feature_segment = branch.rsplit("/", 1)[-1]
+
+    # Accept sequential prefix (3+ digits) but exclude malformed timestamps:
+    # 7-or-8 digit date + 6-digit time with no trailing slug.
+    is_sequential = bool(
+        re.match(r"^[0-9]{3,}-", feature_segment)
+        and not re.match(r"^[0-9]{7}-[0-9]{6}-", feature_segment)
+        and not re.fullmatch(r"[0-9]{7,8}-[0-9]{6}", feature_segment)
+    )
+    is_timestamp = bool(re.match(r"^[0-9]{8}-[0-9]{6}-", feature_segment))
+
+    if not is_sequential and not is_timestamp:
+        print(f"ERROR: Not on a feature branch. Current branch: {raw}", file=sys.stderr)
+        print(
+            "Feature branches should be named like: 001-feature-name, "
+            "1234-feature-name, 20260319-143022-feature-name, or "
+            "<prefix>/001-feature-name",
+            file=sys.stderr,
+        )
+        return False
+
+    return True

extensions/git/scripts/python/initialize_repo.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+"""Git extension: initialize_repo.py
+
+Initialize a Git repository with an initial commit.
+Python port of ``initialize-repo.sh`` / ``initialize-repo.ps1``.
+Customizable — replace this script to add .gitignore templates,
+default branch config, git-flow, LFS, signing, etc.
+"""
+
+from __future__ import annotations
+
+import re
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+
+
+def _find_project_root(start: Path) -> Path | None:
+    current = start
+    while True:
+        if (current / ".specify").is_dir() or (current / ".git").exists():
+            return current
+        if current.parent == current:
+            return None
+        current = current.parent
+
+
+def _read_commit_message(repo_root: Path) -> str:
+    """Read init_commit_message from git-config.yml, mirroring the bash sed pipeline."""
+    default = "[Spec Kit] Initial commit"
+    config_file = repo_root / ".specify" / "extensions" / "git" / "git-config.yml"
+    if not config_file.is_file():
+        return default
+    try:
+        lines = config_file.read_text(encoding="utf-8").splitlines()
+    except (OSError, UnicodeDecodeError):
+        return default
+    for line in lines:
+        if line.startswith("init_commit_message:"):
+            value = re.sub(r"^init_commit_message:\s*", "", line)
+            value = re.sub(r"^[\"']", "", value)
+            value = re.sub(r"[\"']*$", "", value)
+            if value:
+                return value
+    return default
+
+
+def main() -> int:
+    script_dir = Path(__file__).resolve().parent
+    repo_root = _find_project_root(script_dir) or Path.cwd()
+
+    commit_msg = _read_commit_message(repo_root)
+
+    if shutil.which("git") is None:
+        print(
+            "[specify] Warning: Git not found; skipped repository initialization",
+            file=sys.stderr,
+        )
+        return 0
+
+    probe = subprocess.run(
+        ["git", "rev-parse", "--is-inside-work-tree"],
+        cwd=repo_root,
+        capture_output=True,
+        text=True,
+    )
+    if probe.returncode == 0:
+        print("[specify] Git repository already initialized; skipping", file=sys.stderr)
+        return 0
+
+    steps = [
+        (["git", "init", "-q"], "git init"),
+        (["git", "add", "."], "git add"),
+        (["git", "commit", "--allow-empty", "-q", "-m", commit_msg], "git commit"),
+    ]
+    for cmd, label in steps:
+        result = subprocess.run(cmd, cwd=repo_root, capture_output=True, text=True)
+        if result.returncode != 0:
+            output = (result.stdout + result.stderr).strip()
+            print(f"[specify] Error: {label} failed: {output}", file=sys.stderr)
+            return 1
+
+    print("[OK] Git repository initialized", file=sys.stderr)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

extensions/selftest/commands/selftest.md

@@ -48,7 +48,7 @@ cat .specify/extensions/.registry/$ARGUMENTS.json
 
 ### Step 4: Verification Report
 
-Analyze the standard output of the three steps. 
+Analyze the standard output of the three steps.
 Generate a terminal-style test output format detailing the results of discovery, installation, and registration. Return this directly to the user.
 
 Example output format:

newsletters/2026-March.md

@@ -76,5 +76,3 @@ Areas under discussion or in progress for future development:
 - **Continued agent expansion** -- seven new agents were added in March alone. The agent-agnostic design means support for emerging tools can be added by anyone. [\[byteiota.com\]](https://byteiota.com/spec-driven-development-kills-vibe-coding-march-2026/)
 - **Experience simplification** -- the preset system, custom workflows, and growing walkthrough library lower the learning curve, but extension discoverability will need a more robust solution as the catalog grows. [\[github.com\]](https://github.com/github/spec-kit/releases)
 - **Toward a stable release** -- nine releases in one month reflects pre-1.0 momentum. Reaching 1.0 will require stabilizing the extension and preset APIs and ensuring backward compatibility across the agent and extension surface area. [\[github.com\]](https://github.com/github/spec-kit/blob/main/newsletters/2026-February.md)
-
-

presets/ARCHITECTURE.md

@@ -158,8 +158,7 @@ presets/
         ├── plan-template.md
         ├── tasks-template.md
         ├── checklist-template.md
-        ├── constitution-template.md
-        └── agent-file-template.md
+        └── constitution-template.md
 ```
 
 ## Module Structure

presets/catalog.community.json

@@ -1,6 +1,6 @@
 {
   "schema_version": "1.0",
-  "updated_at": "2026-06-30T00:00:00Z",
+  "updated_at": "2026-07-14T00:00:00Z",
   "catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/presets/catalog.community.json",
   "presets": {
     "a11y-governance": {
@@ -131,6 +131,35 @@
       "created_at": "2026-04-27T00:00:00Z",
       "updated_at": "2026-06-14T00:00:00Z"
     },
+    "autonomous-run-governance": {
+      "name": "Autonomous Run Governance",
+      "id": "autonomous-run-governance",
+      "version": "0.1.4",
+      "description": "Adds permission-bounded, evidence-first governance for autonomous Spec Kit delivery, convergence, resume, closeout, and retrospective learning.",
+      "author": "Thorsten Hindermann",
+      "repository": "https://github.com/hindermath/spec-kit-preset-autonomous-run-governance",
+      "download_url": "https://github.com/hindermath/spec-kit-preset-autonomous-run-governance/archive/refs/tags/v0.1.4.zip",
+      "homepage": "https://github.com/hindermath/spec-kit-preset-autonomous-run-governance",
+      "documentation": "https://github.com/hindermath/spec-kit-preset-autonomous-run-governance/blob/v0.1.4/README.md",
+      "license": "MIT",
+      "requires": {
+        "speckit_version": ">=0.8.3"
+      },
+      "provides": {
+        "templates": 12,
+        "commands": 2,
+        "scripts": 2
+      },
+      "tags": [
+        "autonomous",
+        "governance",
+        "evidence",
+        "permissions",
+        "retrospective"
+      ],
+      "created_at": "2026-07-13T00:00:00Z",
+      "updated_at": "2026-07-14T00:00:00Z"
+    },
     "canon-core": {
       "name": "Canon Core",
       "id": "canon-core",
@@ -618,6 +647,34 @@
       "created_at": "2026-04-30T00:00:00Z",
       "updated_at": "2026-04-30T00:00:00Z"
     },
+    "test-first-governance": {
+      "name": "Test-First Governance",
+      "id": "test-first-governance",
+      "version": "1.3.0",
+      "description": "Governs TDD with coverage-complete BDD/ATDD Gherkin scenarios, explicit suite ownership, professional test reports, traceability, and risk-based quality gates.",
+      "author": "Zoltán Katona, PhD",
+      "repository": "https://github.com/ka-zo/spec-kit-preset-test-first-governance",
+      "download_url": "https://github.com/ka-zo/spec-kit-preset-test-first-governance/archive/refs/tags/1.3.0.zip",
+      "homepage": "https://github.com/ka-zo/spec-kit-preset-test-first-governance",
+      "documentation": "https://github.com/ka-zo/spec-kit-preset-test-first-governance/blob/main/README.md",
+      "license": "MIT",
+      "requires": {
+        "speckit_version": ">=0.12.11"
+      },
+      "provides": {
+        "templates": 10,
+        "commands": 8
+      },
+      "tags": [
+        "tdd",
+        "bdd",
+        "atdd",
+        "quality-gates",
+        "traceability"
+      ],
+      "created_at": "2026-07-13T00:00:00Z",
+      "updated_at": "2026-07-13T00:00:00Z"
+    },
     "toc-navigation": {
       "name": "Table of Contents Navigation",
       "id": "toc-navigation",

presets/self-test/preset.yml

@@ -44,12 +44,6 @@ provides:
       description: "Self-test constitution template"
       replaces: "constitution-template"
 
-    - type: "template"
-      name: "agent-file-template"
-      file: "templates/agent-file-template.md"
-      description: "Self-test agent file template"
-      replaces: "agent-file-template"
-
     - type: "command"
       name: "speckit.specify"
       file: "commands/speckit.specify.md"

presets/self-test/templates/agent-file-template.md

@@ -1,9 +0,0 @@
-# Agent File (Self-Test Preset)
-
-<!-- preset:self-test -->
-
-> This template is provided by the self-test preset.
-
-## Agent Instructions
-
-Follow these guidelines when working on this project.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "specify-cli"
-version = "0.12.10.dev0"
+version = "0.12.16"
 description = "Specify CLI, part of GitHub Spec Kit. A tool to bootstrap your projects for Spec-Driven Development (SDD)."
 readme = "README.md"
 requires-python = ">=3.11"
@@ -83,4 +83,3 @@ extend-select = [
     "S604",  # call-with-shell-equals-true
     "S605",  # start-process-with-a-shell
 ]
-

scripts/bash/check-prerequisites.sh

@@ -57,13 +57,13 @@ OPTIONS:
 EXAMPLES:
   # Check task prerequisites (plan.md required)
   ./check-prerequisites.sh --json
-  
+
   # Check implementation prerequisites (plan.md + tasks.md required)
   ./check-prerequisites.sh --json --require-tasks --include-tasks
-  
+
   # Get feature paths only (no validation)
   ./check-prerequisites.sh --paths-only
-  
+
 EOF
             exit 0
             ;;
@@ -182,13 +182,13 @@ else
     # Text output
     echo "FEATURE_DIR:$FEATURE_DIR"
     echo "AVAILABLE_DOCS:"
-    
+
     # Show status of each potential document
     check_file "$RESEARCH" "research.md"
     check_file "$DATA_MODEL" "data-model.md"
     check_dir "$CONTRACTS_DIR" "contracts/"
     check_file "$QUICKSTART" "quickstart.md"
-    
+
     if $INCLUDE_TASKS; then
         check_file "$TASKS" "tasks.md"
     fi

scripts/bash/create-new-feature.sh

@@ -94,7 +94,7 @@ fi
 get_highest_from_specs() {
     local specs_dir="$1"
     local highest=0
-    
+
     if [ -d "$specs_dir" ]; then
         for dir in "$specs_dir"/*; do
             [ -d "$dir" ] || continue
@@ -109,7 +109,7 @@ get_highest_from_specs() {
             fi
         done
     fi
-    
+
     echo "$highest"
 }
 
@@ -135,19 +135,19 @@ fi
 # Function to generate branch name with stop word filtering and length filtering
 generate_branch_name() {
     local description="$1"
-    
+
     # Common stop words to filter out
     local stop_words="^(i|a|an|the|to|for|of|in|on|at|by|with|from|is|are|was|were|be|been|being|have|has|had|do|does|did|will|would|should|could|can|may|might|must|shall|this|that|these|those|my|your|our|their|want|need|add|get|set)$"
-    
+
     # Convert to lowercase and split into words
     local clean_name=$(printf '%s' "$description" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/ /g')
-    
+
     # Filter words: remove stop words and words shorter than 3 chars (unless they're uppercase acronyms in original)
     local meaningful_words=()
     for word in $clean_name; do
         # Skip empty words
         [ -z "$word" ] && continue
-        
+
         # Keep words that are NOT stop words AND (length >= 3 OR are potential acronyms)
         if ! echo "$word" | grep -qiE "$stop_words"; then
             if [ ${#word} -ge 3 ]; then
@@ -160,12 +160,12 @@ generate_branch_name() {
             fi
         fi
     done
-    
+
     # If we have meaningful words, use first 3-4 of them
     if [ ${#meaningful_words[@]} -gt 0 ]; then
         local max_words=3
         if [ ${#meaningful_words[@]} -eq 4 ]; then max_words=4; fi
-        
+
         local result=""
         local count=0
         for word in "${meaningful_words[@]}"; do
@@ -221,15 +221,15 @@ if [ ${#BRANCH_NAME} -gt $MAX_BRANCH_LENGTH ]; then
     # Account for prefix length: timestamp (15) + hyphen (1) = 16, or sequential (3) + hyphen (1) = 4
     PREFIX_LENGTH=$(( ${#FEATURE_NUM} + 1 ))
     MAX_SUFFIX_LENGTH=$((MAX_BRANCH_LENGTH - PREFIX_LENGTH))
-    
+
     # Truncate suffix at word boundary if possible
     TRUNCATED_SUFFIX=$(echo "$BRANCH_SUFFIX" | cut -c1-$MAX_SUFFIX_LENGTH)
     # Remove trailing hyphen if truncation created one
     TRUNCATED_SUFFIX=$(echo "$TRUNCATED_SUFFIX" | sed 's/-$//')
-    
+
     ORIGINAL_BRANCH_NAME="$BRANCH_NAME"
     BRANCH_NAME="${FEATURE_NUM}-${TRUNCATED_SUFFIX}"
-    
+
     >&2 echo "[specify] Warning: Branch name exceeded GitHub's 244-byte limit"
     >&2 echo "[specify] Original: $ORIGINAL_BRANCH_NAME (${#ORIGINAL_BRANCH_NAME} bytes)"
     >&2 echo "[specify] Truncated to: $BRANCH_NAME (${#BRANCH_NAME} bytes)"

scripts/bash/setup-plan.sh

@@ -8,17 +8,17 @@ ARGS=()
 
 for arg in "$@"; do
     case "$arg" in
-        --json) 
-            JSON_MODE=true 
+        --json)
+            JSON_MODE=true
             ;;
-        --help|-h) 
+        --help|-h)
             echo "Usage: $0 [--json]"
             echo "  --json    Output results in JSON format"
             echo "  --help    Show this help message"
-            exit 0 
+            exit 0
             ;;
-        *) 
-            ARGS+=("$arg") 
+        *)
+            ARGS+=("$arg")
             ;;
     esac
 done
@@ -77,8 +77,7 @@ if $JSON_MODE; then
     fi
 else
     echo "FEATURE_SPEC: $FEATURE_SPEC"
-    echo "IMPL_PLAN: $IMPL_PLAN" 
+    echo "IMPL_PLAN: $IMPL_PLAN"
     echo "SPECS_DIR: $FEATURE_DIR"
     echo "BRANCH: $CURRENT_BRANCH"
 fi
-

scripts/powershell/check-prerequisites.ps1

@@ -42,10 +42,10 @@ OPTIONS:
 EXAMPLES:
   # Check task prerequisites (plan.md required)
   .\check-prerequisites.ps1 -Json
-  
+
   # Check implementation prerequisites (plan.md + tasks.md required)
   .\check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks
-  
+
   # Get feature paths only (no validation)
   .\check-prerequisites.ps1 -PathsOnly
 
@@ -118,35 +118,35 @@ if (Test-Path $paths.RESEARCH) { $docs += 'research.md' }
 if (Test-Path $paths.DATA_MODEL) { $docs += 'data-model.md' }
 
 # Check contracts directory (only if it exists and has files)
-if ((Test-Path $paths.CONTRACTS_DIR) -and (Get-ChildItem -Path $paths.CONTRACTS_DIR -ErrorAction SilentlyContinue | Select-Object -First 1)) { 
-    $docs += 'contracts/' 
+if ((Test-Path $paths.CONTRACTS_DIR) -and (Get-ChildItem -Path $paths.CONTRACTS_DIR -ErrorAction SilentlyContinue | Select-Object -First 1)) {
+    $docs += 'contracts/'
 }
 
 if (Test-Path $paths.QUICKSTART) { $docs += 'quickstart.md' }
 
 # Include tasks.md if requested and it exists
-if ($IncludeTasks -and (Test-Path $paths.TASKS)) { 
-    $docs += 'tasks.md' 
+if ($IncludeTasks -and (Test-Path $paths.TASKS)) {
+    $docs += 'tasks.md'
 }
 
 # Output results
 if ($Json) {
     # JSON output
-    [PSCustomObject]@{ 
+    [PSCustomObject]@{
         FEATURE_DIR = $paths.FEATURE_DIR
-        AVAILABLE_DOCS = $docs 
+        AVAILABLE_DOCS = $docs
     } | ConvertTo-Json -Compress
 } else {
     # Text output
     Write-Output "FEATURE_DIR:$($paths.FEATURE_DIR)"
     Write-Output "AVAILABLE_DOCS:"
-    
+
     # Show status of each potential document
     Test-FileExists -Path $paths.RESEARCH -Description 'research.md' | Out-Null
     Test-FileExists -Path $paths.DATA_MODEL -Description 'data-model.md' | Out-Null
     Test-DirHasFiles -Path $paths.CONTRACTS_DIR -Description 'contracts/' | Out-Null
     Test-FileExists -Path $paths.QUICKSTART -Description 'quickstart.md' | Out-Null
-    
+
     if ($IncludeTasks) {
         Test-FileExists -Path $paths.TASKS -Description 'tasks.md' | Out-Null
     }

scripts/powershell/common.ps1

@@ -191,7 +191,7 @@ function Get-FeaturePathsEnv {
         [Console]::Error.WriteLine("ERROR: Feature directory not found. Set SPECIFY_FEATURE_DIRECTORY or run the specify command to create .specify/feature.json.")
         exit 1
     }
-    
+
     # When no branch context exists (no SPECIFY_FEATURE, feature resolved via
     # SPECIFY_FEATURE_DIRECTORY or feature.json), fall back to the feature
     # directory basename so CURRENT_BRANCH is a usable identifier rather than

scripts/powershell/setup-plan.ps1

@@ -63,7 +63,7 @@ if (Test-Path $paths.IMPL_PLAN -PathType Leaf) {
 
 # Output results
 if ($Json) {
-    $result = [PSCustomObject]@{ 
+    $result = [PSCustomObject]@{
         FEATURE_SPEC = $paths.FEATURE_SPEC
         IMPL_PLAN = $paths.IMPL_PLAN
         SPECS_DIR = $paths.FEATURE_DIR

spec-kit.code-workspace

@@ -5,4 +5,4 @@
 		}
 	],
 	"settings": {}
-}
+}

src/specify_cli/_github_http.py

@@ -24,6 +24,7 @@ GITHUB_HOSTS = frozenset({
     "api.github.com",
     "codeload.github.com",
 })
+_MAX_RELEASE_METADATA_BYTES = 5 * 1024 * 1024
 
 
 def build_github_request(url: str) -> urllib.request.Request:
@@ -68,6 +69,8 @@ def resolve_github_release_asset_api_url(
     open_url_fn: Callable,
     timeout: int = 60,
     github_hosts: tuple[str, ...] = (),
+    redirect_validator: Callable[[str, str], None] | None = None,
+    max_metadata_bytes: int = _MAX_RELEASE_METADATA_BYTES,
 ) -> Optional[str]:
     """Resolve a GitHub release browser-download URL to its REST API asset URL.
 
@@ -91,6 +94,8 @@ def resolve_github_release_asset_api_url(
             authenticated release-metadata lookup.
         timeout: Per-request timeout in seconds.
         github_hosts: Host patterns to treat as GitHub Enterprise Server.
+        redirect_validator: Optional policy applied to metadata redirects.
+        max_metadata_bytes: Maximum release-metadata response size.
     """
     import json
     import urllib.error
@@ -149,13 +154,33 @@ def resolve_github_release_asset_api_url(
     release_url = f"{api_base}/repos/{owner}/{repo}/releases/tags/{encoded_tag}"
 
     try:
-        with open_url_fn(release_url, timeout=timeout) as response:
-            release_data = json.loads(response.read())
-    except (urllib.error.URLError, json.JSONDecodeError):
+        open_kwargs = {"timeout": timeout}
+        if redirect_validator is not None:
+            open_kwargs["redirect_validator"] = redirect_validator
+        with open_url_fn(release_url, **open_kwargs) as response:
+            raw_release_data = response.read(max_metadata_bytes + 1)
+            if len(raw_release_data) > max_metadata_bytes:
+                raise ValueError("GitHub release metadata exceeds size limit")
+            release_data = json.loads(raw_release_data)
+    except (
+        urllib.error.URLError,
+        json.JSONDecodeError,
+        TypeError,
+        ValueError,
+    ):
         return None
 
-    for asset in release_data.get("assets", []):
-        if asset.get("name") == asset_name and asset.get("url"):
+    if not isinstance(release_data, dict):
+        return None
+    assets = release_data.get("assets", [])
+    if not isinstance(assets, list):
+        return None
+    for asset in assets:
+        if (
+            isinstance(asset, dict)
+            and asset.get("name") == asset_name
+            and asset.get("url")
+        ):
             return str(asset["url"])
 
     return None

src/specify_cli/_init_options.py

@@ -14,7 +14,7 @@ def save_init_options(project_path: Path, options: dict[str, Any]) -> None:
     dest = project_path / INIT_OPTIONS_FILE
     dest.parent.mkdir(parents=True, exist_ok=True)
     dest.write_text(
-        json.dumps(options, indent=2, sort_keys=True, ensure_ascii=False),
+        json.dumps(options, indent=2, sort_keys=True, ensure_ascii=False) + "\n",
         encoding="utf-8",
     )
 

src/specify_cli/agents.py

@@ -213,6 +213,52 @@ class CommandRegistrar:
             ".specify.specify/", ".specify/"
         )
 
+    @staticmethod
+    def rewrite_extension_paths(
+        text: str, extension_id: str, extension_dir: Path
+    ) -> str:
+        """Rewrite extension-relative paths to their installed locations.
+
+        Extension command bodies reference bundled files relative to the
+        extension root (e.g. ``agents/control/commander.md``). After install
+        those files live under ``.specify/extensions/<id>/``, so bare
+        references would resolve against the workspace root and never be
+        found (#2101).
+
+        Only directories that actually exist inside *extension_dir* are
+        rewritten, keeping the behaviour conservative and avoiding false
+        positives on prose. ``commands`` (slash-command sources), ``specs``
+        (user project artifacts) and dot-directories are never rewritten.
+        """
+        if not isinstance(text, str) or not text:
+            return text
+
+        skip = {"commands", ".git", "specs"}
+        try:
+            subdirs = [
+                entry.name
+                for entry in extension_dir.iterdir()
+                if entry.is_dir()
+                and entry.name not in skip
+                and not entry.name.startswith(".")
+            ]
+        except OSError:
+            return text
+
+        for subdir in subdirs:
+            # Only rewrite relative references (subdir/... or ./subdir/...);
+            # absolute paths like /subdir/... keep their meaning. Use a
+            # callable replacement: subdir/extension_id come from the
+            # filesystem and could contain backslashes or "\1"-like
+            # sequences, which would corrupt a string replacement template.
+            replacement = f".specify/extensions/{extension_id}/{subdir}/"
+            text = re.sub(
+                r'(^|[\s`"\'(])(?:\./)?' + re.escape(subdir) + "/",
+                lambda m: m.group(1) + replacement,
+                text,
+            )
+        return text
+
     def render_markdown_command(
         self, frontmatter: dict, body: str, source_id: str, context_note: str = None
     ) -> str:
@@ -639,6 +685,9 @@ class CommandRegistrar:
                         frontmatter[key] = core_frontmatter[key]
                 frontmatter.pop("strategy", None)
 
+            if extension_id:
+                body = self.rewrite_extension_paths(body, extension_id, source_root)
+
             frontmatter = self._adjust_script_paths(
                 frontmatter, extension_id=extension_id
             )

src/specify_cli/authentication/config.py

@@ -196,7 +196,15 @@ def find_entries_for_url(
     url: str, entries: list[AuthConfigEntry]
 ) -> list[AuthConfigEntry]:
     """Return entries whose ``hosts`` match the hostname of *url*."""
-    hostname = (urlparse(url).hostname or "").lower()
+    # A malformed authority (e.g. an unterminated IPv6 bracket "https://[::1")
+    # makes urlparse/hostname raise ValueError. Treat that the same as a
+    # host-less URL: no entry can match, so return no matches rather than
+    # leaking a raw ValueError out of the shared HTTP client (build_request /
+    # open_url call this before any URL validation).
+    try:
+        hostname = (urlparse(url).hostname or "").lower()
+    except ValueError:
+        return []
     if not hostname:
         return []
     return [

src/specify_cli/bundler/lib/yamlio.py

@@ -10,6 +10,8 @@ from __future__ import annotations
 import json
 import os
 import re
+import stat
+import tempfile
 from pathlib import Path, PurePosixPath
 from typing import Any
 
@@ -87,17 +89,63 @@ def loads_json(text: str, *, origin: str = "<string>") -> Any:
 
 
 def dump_json(path: Path, data: Any, *, within: Path | None = None) -> Path:
-    """Write *data* as pretty JSON to *path* (optionally confined to *within*)."""
+    """Atomically write pretty JSON to *path* (optionally confined to *within*)."""
     path = Path(path)
     if within is not None:
         path = ensure_within(within, path)
+    fd = -1
+    temp_path: Path | None = None
     try:
         path.parent.mkdir(parents=True, exist_ok=True)
-        with path.open("w", encoding="utf-8") as handle:
+        fd, temp_name = tempfile.mkstemp(
+            dir=path.parent,
+            prefix=f".{path.name}.",
+            suffix=".tmp",
+        )
+        temp_path = Path(temp_name)
+        with os.fdopen(os.dup(fd), "w", encoding="utf-8") as handle:
             json.dump(data, handle, indent=2, sort_keys=False)
             handle.write("\n")
+
+        try:
+            if path.exists():
+                existing = path.stat(follow_symlinks=False)
+                if stat.S_ISREG(existing.st_mode) and hasattr(os, "fchmod"):
+                    os.fchmod(fd, stat.S_IMODE(existing.st_mode))
+                if stat.S_ISREG(existing.st_mode) and hasattr(os, "fchown"):
+                    try:
+                        os.fchown(fd, existing.st_uid, existing.st_gid)
+                    except PermissionError:
+                        pass
+        except OSError:
+            pass
+
+        staged = os.stat(temp_path, follow_symlinks=False)
+        opened = os.fstat(fd)
+        if (
+            not stat.S_ISREG(staged.st_mode)
+            or staged.st_dev != opened.st_dev
+            or staged.st_ino != opened.st_ino
+        ):
+            raise OSError("staged JSON file changed before commit")
+
+        os.close(fd)
+        fd = -1
+        os.replace(temp_path, path)
+        temp_path = None
     except OSError as exc:
         raise BundlerError(f"Could not write {path}: {exc}") from exc
+    finally:
+        if fd >= 0:
+            try:
+                os.close(fd)
+            except OSError:
+                pass
+        if temp_path is not None:
+            try:
+                temp_path.unlink(missing_ok=True)
+            except OSError:
+                pass
     return path
 
 

src/specify_cli/bundler/services/adapters.py

@@ -68,8 +68,18 @@ def _validate_remote_url(source_id: str, url: str) -> None:
     Mirrors ``specify_cli.catalogs`` URL validation to avoid MITM/downgrade
     issues before any network call.
     """
-    parsed = urlparse(url)
-    is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+    # A malformed authority (e.g. an unclosed IPv6 bracket ``https://[::1``)
+    # makes urlparse / hostname access raise ValueError. This function's
+    # contract is to raise BundlerError for a bad URL, so surface that as a
+    # clean error rather than leaking a raw ValueError to the caller.
+    try:
+        parsed = urlparse(url)
+        hostname = parsed.hostname
+    except ValueError:
+        raise BundlerError(
+            f"Catalog '{source_id}' URL is malformed: {url}"
+        ) from None
+    is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
     if parsed.scheme != "https" and not (parsed.scheme == "http" and is_localhost):
         raise BundlerError(
             f"Catalog '{source_id}' URL must use HTTPS (got {parsed.scheme}://). "
@@ -79,7 +89,7 @@ def _validate_remote_url(source_id: str, url: str) -> None:
     # "https://:8080" or "https://user@...", so requiring netloc would let
     # those through even though they carry no host. hostname is None in those
     # cases. Mirrors the fix in ``specify_cli.catalogs`` (#3210).
-    if not parsed.hostname:
+    if not hostname:
         raise BundlerError(
             f"Catalog '{source_id}' URL must be a valid URL with a host: {url}"
         )

src/specify_cli/bundler/services/installer.py

@@ -187,19 +187,41 @@ def remove_bundle(
 
     still_needed = components_still_needed(records, exclude_bundle_id=bundle_id)
     result = InstallResult(bundle_id=bundle_id)
+    remove_attempted = False
 
-    for component in target.contributed_components:
-        key = (component.kind, component.id)
-        if key in still_needed:
-            result.skipped.append(component)
-            continue
-        if installer.is_installed(project_root, component):
-            installer.remove(project_root, component)
-            result.uninstalled.append(component)
+    try:
+        for component in target.contributed_components:
+            key = (component.kind, component.id)
+            if key in still_needed:
+                result.skipped.append(component)
+                continue
+            if installer.is_installed(project_root, component):
+                remove_attempted = True
+                installer.remove(project_root, component)
+                result.uninstalled.append(component)
+        save_records(project_root, remove_record(records, bundle_id))
+    except Exception as exc:  # noqa: BLE001
+        if result.uninstalled:
+            detail = (
+                f"{len(result.uninstalled)} component(s) were already removed "
+                "before this failure; the bundle record was left unchanged, "
+                "so the project may be partially uninstalled."
+            )
+        elif remove_attempted:
+            detail = (
+                "No components were removed, but the failing component may "
+                "have made partial changes before raising, so the project "
+                "may be partially uninstalled."
+            )
         else:
-            result.skipped.append(component)
+            detail = (
+                "No components were removed and no removal was attempted; "
+                "the bundle record was left unchanged."
+            )
+        raise BundlerError(
+            f"Failed to remove bundle '{bundle_id}': {exc}. {detail}"
+        ) from exc
 
-    save_records(project_root, remove_record(records, bundle_id))
     return result
 
 

src/specify_cli/catalogs.py

@@ -71,8 +71,12 @@ class CatalogStackBase:
         """Validate that a catalog URL uses HTTPS, except localhost HTTP."""
         from urllib.parse import urlparse
 
-        parsed = urlparse(url)
-        is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+        try:
+            parsed = urlparse(url)
+            hostname = parsed.hostname
+        except ValueError:
+            raise cls._error(f"Catalog URL is malformed: {url}") from None
+        is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
         if parsed.scheme != "https" and not (parsed.scheme == "http" and is_localhost):
             raise cls._error(
                 f"Catalog URL must use HTTPS (got {parsed.scheme}://). "
@@ -81,7 +85,7 @@ class CatalogStackBase:
         # Check hostname, not netloc: netloc is truthy for host-less URLs like
         # "https://:8080" or "https://user@", so the host guarantee this error
         # promises would not actually hold. hostname is None in those cases (#3209).
-        if not parsed.hostname:
+        if not hostname:
             raise cls._error("Catalog URL must be a valid URL with a host.")
 
     def _load_catalog_config(self, config_path: Path) -> list[CatalogEntry] | None:

src/specify_cli/commands/bundle/__init__.py

@@ -746,11 +746,16 @@ def _resolve_manifest_path(path: Path | None) -> Path:
 def _download_manifest(resolved, *, offline: bool):
     """Resolve a bundle's manifest from its catalog ``download_url``.
 
-    Local/``file://`` URLs always work offline and may point at a ``.zip``
-    artifact, a bundle directory, or a ``bundle.yml`` (handled by
-    :func:`_local_manifest_source`). Remote ``https://`` URLs are fetched with
-    the shared authenticated, redirect-validated HTTP client, and only when not
-    ``--offline``.
+    Catalog ``download_url``s are HTTPS-only (``http`` allowed for localhost),
+    matching the extensions/presets/workflows catalog systems. Remote URLs are
+    fetched with the shared authenticated, redirect-validated HTTP client, and
+    only when not ``--offline``.
+
+    Local and ``file://`` sources are intentionally not resolved here: to
+    install a bundle from disk, pass the path positionally
+    (``specify bundle install ./path/to/bundle.yml`` — a bundle directory or a
+    ``.zip`` artifact also works), which :func:`_local_manifest_source` handles
+    before catalog resolution and which never touches ``download_url``.
     """
     from urllib.parse import urlparse
 
@@ -763,26 +768,35 @@ def _download_manifest(resolved, *, offline: bool):
     parsed = urlparse(url)
     scheme = parsed.scheme.lower()
 
-    # On Windows an absolute path like ``C:\bundle.yml`` parses with a
-    # single-letter ``scheme``; treat it as a local file, not a URL scheme.
+    # ``file://`` URLs and bare filesystem paths (including Windows drive paths
+    # like ``C:\bundle.yml``, which urlparse reads as a single-letter scheme)
+    # are not valid catalog download URLs. Catalog URLs are HTTPS-only across
+    # every catalog system; installing from disk is done by passing the path
+    # positionally, which never reaches URL resolution. Give an actionable
+    # error rather than accepting a scheme the rest of the codebase rejects.
     if scheme in ("", "file") or re.match(r"^[A-Za-z]:[\\/]", url):
-        local = Path(parsed.path if scheme == "file" else url)
-        manifest = _local_manifest_source(str(local))
-        if manifest is None:
-            raise BundlerError(f"Bundle manifest not found: {local}")
-        return manifest
+        raise BundlerError(
+            f"Catalog entry '{resolved.entry.id}' has a non-HTTP(S) download_url "
+            f"({url}); catalog download URLs must be HTTPS (http for localhost) — "
+            "a file:// URL, a local filesystem path, or a scheme-less value "
+            "(e.g. 'example.com/bundle.zip') is not accepted. "
+            "To install a bundle from disk, pass the path directly: "
+            "'specify bundle install <path-to-bundle.yml | bundle-dir | .zip>'."
+        )
 
-    if scheme in ("http", "https"):
-        if offline:
-            raise BundlerError(
-                f"Network access disabled; cannot download bundle '{resolved.entry.id}' "
-                f"from {url}."
-            )
-        return _download_remote_manifest(resolved.entry.id, url)
+    # Validate the scheme/host *before* the offline gate so an invalid or
+    # non-HTTPS download_url reports the real problem in every mode, rather
+    # than a misleading "Network access disabled" under --offline.
+    # (_download_remote_manifest re-checks this, but only once network access
+    # is permitted.) HTTPS-only, http allowed for localhost.
+    _require_https(f"bundle '{resolved.entry.id}'", url)
 
-    raise BundlerError(
-        f"Unsupported download_url scheme for bundle '{resolved.entry.id}': {url}"
-    )
+    if offline:
+        raise BundlerError(
+            f"Network access disabled; cannot download bundle '{resolved.entry.id}' "
+            f"from {url}."
+        )
+    return _download_remote_manifest(resolved.entry.id, url)
 
 
 def _require_https(label: str, url: str) -> None:

src/specify_cli/commands/init.py

@@ -33,11 +33,17 @@ def _stdin_is_interactive() -> bool:
 def ensure_constitution_from_template(
     project_path: Path, tracker: StepTracker | None = None
 ) -> None:
-    """Copy constitution template to memory if it doesn't exist."""
+    """Materialize the resolved constitution template to memory if missing.
+
+    Resolution walks the full priority stack (project overrides → installed
+    presets → extensions → core) via :class:`PresetResolver`, so a preset that
+    ships a ``constitution-template`` (e.g. ``strategy: replace`` with a ratified
+    constitution) can seed the memory file. When nothing overrides it, the
+    resolver falls through to the core template.
+    """
+    from ..presets import _materialize_constitution_template
+
     memory_constitution = project_path / ".specify" / "memory" / "constitution.md"
-    template_constitution = (
-        project_path / ".specify" / "templates" / "constitution-template.md"
-    )
 
     if memory_constitution.exists():
         if tracker:
@@ -45,18 +51,21 @@ def ensure_constitution_from_template(
             tracker.skip("constitution", "existing file preserved")
         return
 
-    if not template_constitution.exists():
-        if tracker:
-            tracker.add("constitution", "Constitution setup")
-            tracker.error("constitution", "template not found")
-        return
-
     try:
-        memory_constitution.parent.mkdir(parents=True, exist_ok=True)
-        shutil.copy2(template_constitution, memory_constitution)
+        materialization = _materialize_constitution_template(
+            project_path, memory_constitution
+        )
+        if materialization is None:
+            if tracker:
+                tracker.add("constitution", "Constitution setup")
+                tracker.error("constitution", "template not found")
+            return
         if tracker:
             tracker.add("constitution", "Constitution setup")
-            tracker.complete("constitution", "copied from template")
+            if materialization == "copied":
+                tracker.complete("constitution", "copied from template")
+            else:
+                tracker.complete("constitution", "composed from template")
         else:
             console.print("[cyan]Initialized constitution from template[/cyan]")
     except Exception as e:
@@ -220,16 +229,45 @@ def register(app: typer.Typer) -> None:
                 console.print(
                     f"[yellow]Warning:[/yellow] Current directory is not empty ({len(existing_items)} items)"
                 )
-                console.print(
-                    "[yellow]Template files will be merged with existing content and may overwrite existing files[/yellow]"
-                )
                 if force:
+                    # Proceeding: the merge/overwrite warning is accurate here.
+                    console.print(
+                        "[yellow]Template files will be merged with existing content and may overwrite existing files[/yellow]"
+                    )
                     console.print(
                         "[cyan]--force supplied: skipping confirmation and proceeding with merge[/cyan]"
                     )
                 else:
-                    response = typer.confirm("Do you want to continue?")
-                    if not response:
+                    # Fold the merge risk into the confirmation prompt rather than
+                    # printing it unconditionally first: on the EOF/no-input path
+                    # below the command exits without changing anything, so a
+                    # standalone "will be merged" line would mislead. Interactive
+                    # users still see the risk as part of the question.
+                    #
+                    # Call typer.confirm normally so piped y/n is honored — e.g.
+                    # `echo y | specify init --here` keeps reaching the
+                    # non-destructive preserve-merge path.
+                    try:
+                        proceed = typer.confirm(
+                            "Template files will be merged with existing content "
+                            "and may overwrite existing files. Do you want to continue?"
+                        )
+                    except (typer.Abort, EOFError):
+                        # typer.confirm raises Abort for BOTH an interactive Ctrl+C
+                        # and an EOF on closed/empty stdin. Distinguish them: a real
+                        # TTY cancellation is a normal exit (0, "cancelled"), while a
+                        # missing-input EOF (non-interactive) becomes an actionable
+                        # error pointing at --force.
+                        if _stdin_is_interactive():
+                            console.print("[yellow]Operation cancelled[/yellow]")
+                            raise typer.Exit(0) from None
+                        console.print(
+                            "[red]Error:[/red] Current directory is not empty and no "
+                            "confirmation input is available. Re-run with "
+                            "[bold]--force[/bold] to merge into it."
+                        )
+                        raise typer.Exit(1) from None
+                    if not proceed:
                         console.print("[yellow]Operation cancelled[/yellow]")
                         raise typer.Exit(0)
         else:
@@ -447,8 +485,6 @@ def register(app: typer.Typer) -> None:
                     "shared-infra", f"scripts ({selected_script}) + templates"
                 )
 
-                ensure_constitution_from_template(project_path, tracker=tracker)
-
                 try:
                     bundled_wf = _locate_bundled_workflow("speckit")
                     if bundled_wf:
@@ -576,6 +612,11 @@ def register(app: typer.Typer) -> None:
                             continuing="Continuing without the optional preset.",
                         )
 
+                # Seed the constitution AFTER preset installation so that a
+                # preset-provided constitution-template (resolved via the
+                # priority stack) wins over the core template.
+                ensure_constitution_from_template(project_path, tracker=tracker)
+
                 tracker.complete("final", "project ready")
             except (typer.Exit, SystemExit):
                 raise

src/specify_cli/extensions/__init__.py

@@ -1078,6 +1078,11 @@ class ExtensionManager:
             frontmatter = registrar._adjust_script_paths(
                 frontmatter, extension_id=manifest.id
             )
+            # Mirror the register_commands() rewrite (#2101): resolve
+            # extension-relative subdir references (agents/, knowledge-base/,
+            # etc.) to their installed .specify/extensions/<id>/ location
+            # before the generic placeholder/path resolution below.
+            body = registrar.rewrite_extension_paths(body, manifest.id, extension_dir)
             body = registrar.resolve_skill_placeholders(
                 selected_ai, frontmatter, body, self.project_root, extension_id=manifest.id
             )
@@ -2732,6 +2737,36 @@ class ConfigManager:
         config_file = self.extension_dir / "local-config.yml"
         return self._load_yaml_config(config_file)
 
+    def _sibling_extension_ids(self) -> list[str]:
+        """Return IDs of other extensions installed alongside this one.
+
+        Sourced from ``ExtensionRegistry`` (``.specify/extensions/.registry``)
+        rather than a directory scan: ``ExtensionManager.remove(...,
+        keep_config=True)`` deliberately preserves the extension directory
+        while dropping the registry entry, so a directory scan would treat
+        that config-only leftover as an installed sibling and keep silently
+        absorbing its ``SPECKIT_<sibling>_*`` env vars into no one. The
+        registry is the source of truth for "installed".
+
+        Returns an empty list if the registry is missing or corrupted
+        (fresh project, ad-hoc test harness) so ``_get_env_config`` degrades
+        to its pre-fix behaviour rather than crashing. ``UnicodeError`` is
+        caught alongside ``OSError`` because ``ExtensionRegistry._load()``
+        opens the file in text mode and only handles ``JSONDecodeError`` /
+        ``FileNotFoundError``, so a registry file with non-UTF-8 bytes would
+        otherwise surface a ``UnicodeDecodeError`` here and break *every*
+        config read instead of degrading gracefully.
+
+        Used by ``_get_env_config`` to detect env vars whose remainder claims
+        a longer, sibling-owned prefix (e.g. ``SPECKIT_GIT_HOOKS_URL`` is
+        owned by ``git-hooks`` when it is co-installed with ``git``).
+        """
+        extensions_dir = self.project_root / ".specify" / "extensions"
+        try:
+            return list(ExtensionRegistry(extensions_dir).keys())
+        except (OSError, UnicodeError):
+            return []
+
     def _get_env_config(self) -> Dict[str, Any]:
         """Get configuration from environment variables.
 
@@ -2751,22 +2786,70 @@ class ConfigManager:
         ext_id_upper = self.extension_id.replace("-", "_").upper()
         prefix = f"SPECKIT_{ext_id_upper}_"
 
+        # Cross-extension prefix collision: because ``_`` doubles as both the
+        # separator between the extension ID and the config path *and* the
+        # substitute for ``-`` inside an extension ID, an env var like
+        # ``SPECKIT_GIT_HOOKS_URL`` begins with *both* the ``SPECKIT_GIT_``
+        # prefix of the ``git`` extension and the ``SPECKIT_GIT_HOOKS_`` prefix
+        # of a co-installed ``git-hooks`` extension. It logically belongs to
+        # the extension whose normalized ID is the longer, more specific match
+        # — otherwise config intended for one extension silently surfaces
+        # inside another and can drive hooks that only inspect
+        # ``config.<field> is set``. Build the list of sibling-owned
+        # remainder-prefixes here so a later env var can be skipped if it
+        # matches one.
+        sibling_prefixes: list[str] = []
+        for sibling_id in self._sibling_extension_ids():
+            if sibling_id == self.extension_id:
+                continue
+            sib_upper = sibling_id.replace("-", "_").upper()
+            # A sibling collides only when its normalized ID *extends* our own
+            # (i.e. starts with ``<US>_``). ``git`` vs ``not-git`` is not a
+            # collision; ``git`` vs ``git-hooks`` is.
+            if sib_upper.startswith(ext_id_upper + "_"):
+                # The portion of the env-var *remainder* the sibling claims,
+                # including the trailing ``_`` so a shorter ID that shares a
+                # non-boundary prefix cannot false-positive (e.g. sibling
+                # ``hook`` would not eat env vars under key ``hooks``).
+                sibling_prefixes.append(sib_upper[len(ext_id_upper) + 1 :] + "_")
+
         for key, value in os.environ.items():
             if not key.startswith(prefix):
                 continue
 
-            # Remove prefix and split into parts
-            config_path = key[len(prefix) :].lower().split("_")
+            remainder = key[len(prefix) :]
+            # Skip when a longer sibling ID claims this var — see the block
+            # above. Keeps ``SPECKIT_GIT_HOOKS_URL`` out of the ``git``
+            # extension's config when ``git-hooks`` is co-installed.
+            if any(remainder.startswith(sp) for sp in sibling_prefixes):
+                continue
 
-            # Build nested dict
+            # Remove prefix and split into parts. Drop empty components from a
+            # malformed name (e.g. ``SPECKIT_<EXT>_`` with no key, or
+            # consecutive underscores ``SPECKIT_X__Y``) so we never create an
+            # entry under an empty key.
+            config_path = [p for p in remainder.lower().split("_") if p]
+            if not config_path:
+                continue
+
+            # Build nested dict. Two env vars can collide on a prefix, e.g.
+            # SPECKIT_X_CONNECTION=a and SPECKIT_X_CONNECTION_URL=b. Guard the
+            # walk so a colliding scalar is replaced by a dict (deeper/more
+            # specific vars win) instead of being indexed into — which raised
+            # TypeError ('str' object does not support item assignment) — and
+            # guard the leaf so a scalar processed after the nested var does
+            # not clobber the nested dict. Order-independent: both insertion
+            # orders yield {'connection': {'url': ...}}. Nested-wins mirrors
+            # _merge_configs' dict-preserving semantics.
             current = env_config
             for part in config_path[:-1]:
-                if part not in current:
+                if not isinstance(current.get(part), dict):
                     current[part] = {}
                 current = current[part]
 
-            # Set the final value
-            current[config_path[-1]] = value
+            # Set the final value, unless a nested dict already occupies it.
+            if not isinstance(current.get(config_path[-1]), dict):
+                current[config_path[-1]] = value
 
         return env_config
 

src/specify_cli/extensions/_commands.py

@@ -1566,7 +1566,14 @@ def extension_set_priority(
     raw_priority = metadata.get("priority")
     # Only skip if the stored value is already a valid int equal to requested priority
     # This ensures corrupted values (e.g., "high") get repaired even when setting to default (10)
-    if isinstance(raw_priority, int) and raw_priority == priority:
+    # A bool is an int in Python (isinstance(True, int) is True), so exclude it explicitly —
+    # mirroring normalize_priority's bool guard — otherwise a corrupted True/False priority
+    # equals 1/0 here and is never repaired.
+    if (
+        isinstance(raw_priority, int)
+        and not isinstance(raw_priority, bool)
+        and raw_priority == priority
+    ):
         console.print(f"[yellow]Extension '{_escape_markup(str(display_name))}' already has priority {priority}[/yellow]")
         raise typer.Exit(0)
 

src/specify_cli/integrations/_helpers.py

@@ -190,7 +190,15 @@ def _parse_integration_options(integration: Any, raw_options: str) -> dict[str,
     """
     import shlex
     parsed: dict[str, Any] = {}
-    tokens = shlex.split(raw_options)
+    try:
+        tokens = shlex.split(raw_options)
+    except ValueError as exc:
+        # An unbalanced quote (e.g. --integration-options='--commands-dir "foo')
+        # makes shlex raise "No closing quotation". Translate it into the same
+        # clean exit-1 UX as every other bad-input path below rather than
+        # letting a raw traceback escape.
+        console.print(f"[red]Error:[/red] Could not parse integration options: {exc}.")
+        raise typer.Exit(1)
     declared_options = list(integration.options())
     declared = {opt.name.lstrip("-"): opt for opt in declared_options}
     allowed = ", ".join(sorted(opt.name for opt in declared_options))

src/specify_cli/integrations/base.py

@@ -1122,6 +1122,17 @@ class TomlIntegration(IntegrationBase):
 # YamlIntegration — YAML-format agents (Goose)
 # ---------------------------------------------------------------------------
 
+# Characters a YAML literal block scalar cannot carry: C0 controls other
+# than tab/LF (a bare CR acts as a line break inside the scalar), DEL, the
+# C1 range, lone UTF-16 surrogates, and the non-characters U+FFFE/U+FFFF.
+# NEL (U+0085) is YAML-printable but, like LS/PS (U+2028/U+2029), YAML 1.1
+# treats it as a line break, which corrupts the block scalar's structure
+# just the same, so all three are included.
+_YAML_BLOCK_SCALAR_UNSAFE = re.compile(
+    r"[\x00-\x08\x0b-\x1f\x7f-\x9f\u2028\u2029\ud800-\udfff\ufffe\uffff]"
+)
+
+
 class YamlIntegration(IntegrationBase):
     """Concrete base for integrations that use YAML recipe format.
 
@@ -1227,9 +1238,9 @@ class YamlIntegration(IntegrationBase):
     def _render_yaml(cls, title: str, description: str, body: str, source_id: str) -> str:
         """Render a YAML recipe file from title, description, and body.
 
-        Produces a Goose-compatible recipe with a literal block scalar
-        for the prompt content.  Uses ``yaml.safe_dump()`` for the
-        header fields to ensure proper escaping.
+        Produces a Goose-compatible recipe with a literal block scalar for
+        normal prompt content, or an escaped quoted scalar when control
+        characters require it. Uses ``yaml.safe_dump()`` for the header fields.
         """
         header = cls._build_yaml_header(title, description)
 
@@ -1240,6 +1251,23 @@ class YamlIntegration(IntegrationBase):
             default_flow_style=False,
         ).strip()
 
+        # YAML forbids C0 control characters (except tab and newline) and
+        # DEL in every scalar form, and a bare CR acts as a line break
+        # inside a block scalar. A literal block scalar emits such bytes
+        # verbatim, producing a recipe the YAML parser rejects, so fall
+        # back to an escaped double-quoted scalar for those bodies.
+        if _YAML_BLOCK_SCALAR_UNSAFE.search(body):
+            prompt_yaml = yaml.safe_dump(
+                {"prompt": body}, allow_unicode=True, default_style='"', width=sys.maxsize
+            ).strip()
+            lines = [
+                header_yaml,
+                prompt_yaml,
+                "",
+                f"# Source: {source_id}",
+            ]
+            return "\n".join(lines) + "\n"
+
         # Indent the body for YAML block scalar. Use an explicit indentation
         # indicator ("|2") rather than a bare "|": YAML infers a plain block
         # scalar's indentation from its first non-empty line, so a body whose

src/specify_cli/integrations/devin/__init__.py

@@ -62,4 +62,4 @@ class DevinIntegration(SkillsIntegration):
                 default=True,
                 help="Install as agent skills (default for Devin)",
             ),
-        ]
+        ]

src/specify_cli/integrations/forge/__init__.py

@@ -18,13 +18,13 @@ from ..manifest import IntegrationManifest
 
 def format_forge_command_name(cmd_name: str) -> str:
     """Convert command name to Forge-compatible hyphenated format.
-    
+
     Forge requires command names to use hyphens instead of dots for
     compatibility with ZSH and other shells. This function converts
     dot-notation command names to hyphenated format.
-    
+
     The function is idempotent: already-formatted names are returned unchanged.
-    
+
     Examples:
         >>> format_forge_command_name("plan")
         'speckit-plan'
@@ -38,26 +38,26 @@ def format_forge_command_name(cmd_name: str) -> str:
         'speckit-my-extension-example'
         >>> format_forge_command_name("speckit.jira.sync-status")
         'speckit-jira-sync-status'
-    
+
     Args:
-        cmd_name: Command name in dot notation (speckit.foo.bar), 
+        cmd_name: Command name in dot notation (speckit.foo.bar),
                   hyphenated format (speckit-foo-bar), or plain name (foo)
-    
+
     Returns:
         Hyphenated command name with 'speckit-' prefix
     """
     # Already in hyphenated format - return as-is (idempotent)
     if cmd_name.startswith("speckit-"):
         return cmd_name
-    
+
     # Strip 'speckit.' prefix if present
     short_name = cmd_name
     if short_name.startswith("speckit."):
         short_name = short_name[len("speckit."):]
-    
+
     # Replace all dots with hyphens
     short_name = short_name.replace(".", "-")
-    
+
     # Return with 'speckit-' prefix
     return f"speckit-{short_name}"
 

src/specify_cli/integrations/kiro_cli/__init__.py

@@ -13,6 +13,7 @@ _KIRO_ARG_FALLBACK = "(the user will provide the argument in this conversation)"
 
 class KiroCliIntegration(MarkdownIntegration):
     key = "kiro-cli"
+    multi_install_safe = True
     config = {
         "name": "Kiro CLI",
         "folder": ".kiro/",
@@ -26,3 +27,10 @@ class KiroCliIntegration(MarkdownIntegration):
         "args": _KIRO_ARG_FALLBACK,
         "extension": ".md",
     }
+
+    # Kiro CLI keeps everything under a static, isolated agent root
+    # (``.kiro/`` with commands in ``.kiro/prompts``) that no other
+    # integration writes to, so it is safe to install alongside others
+    # (issue #3471). The registry's multi-install-safe contract tests
+    # enforce that isolation for every integration setting this flag.
+    multi_install_safe = True

src/specify_cli/presets/__init__.py

@@ -31,7 +31,117 @@ from ..extensions import REINSTALL_COMMAND, ExtensionRegistry, normalize_priorit
 from .._init_options import is_ai_skills_enabled
 from ..integrations.base import IntegrationBase
 from .._utils import dump_frontmatter, version_satisfies
-from ..shared_infra import verify_archive_sha256
+from ..shared_infra import (
+    _ensure_safe_shared_destination,
+    _ensure_safe_shared_directory,
+    _write_shared_bytes,
+    _write_shared_text,
+    verify_archive_sha256,
+)
+
+
+_CONSTITUTION_PROVENANCE_FILE = ".constitution-template.json"
+
+
+def _content_sha256(content: bytes) -> str:
+    return hashlib.sha256(content).hexdigest()
+
+
+def _constitution_is_generated(
+    project_root: Path,
+    memory_constitution: Path,
+    resolver: "PresetResolver",
+) -> bool:
+    """Return whether the live constitution is an unchanged generated file."""
+    _ensure_safe_shared_destination(project_root, memory_constitution)
+    content = memory_constitution.read_bytes()
+    provenance = memory_constitution.parent / _CONSTITUTION_PROVENANCE_FILE
+    _ensure_safe_shared_destination(project_root, provenance)
+
+    if provenance.exists():
+        try:
+            metadata = json.loads(provenance.read_text(encoding="utf-8"))
+        except (json.JSONDecodeError, UnicodeDecodeError):
+            return False
+        return (
+            isinstance(metadata, dict)
+            and metadata.get("sha256") == _content_sha256(content)
+        )
+
+    # Older projects have no provenance sidecar. Only the immutable bundled or
+    # source-checkout core template is safe to treat as generated.
+    core = resolver._find_bundled_core(
+        "constitution-template", "template", ".md"
+    )
+    return core is not None and core.read_bytes() == content
+
+
+def _constitution_provenance_matches_preset(
+    project_root: Path,
+    memory_constitution: Path,
+    pack_id: str,
+    pack_version: str,
+) -> bool:
+    """Return whether provenance identifies a preset as the materialized source."""
+    provenance = memory_constitution.parent / _CONSTITUTION_PROVENANCE_FILE
+    if not provenance.parent.exists():
+        return False
+    _ensure_safe_shared_destination(project_root, provenance)
+    if not provenance.exists():
+        return False
+    try:
+        metadata = json.loads(provenance.read_text(encoding="utf-8"))
+    except (json.JSONDecodeError, UnicodeDecodeError):
+        return False
+    return (
+        isinstance(metadata, dict)
+        and metadata.get("source") == f"{pack_id} v{pack_version}"
+    )
+
+
+def _materialize_constitution_template(
+    project_root: Path,
+    memory_constitution: Path,
+) -> str | None:
+    """Materialize constitution-template content into memory/constitution.md.
+
+    Returns:
+        "copied" when the winning layer is ``replace`` and the source file is
+        copied verbatim; "composed" when a composing strategy is materialized
+        via ``resolve_content``; ``None`` when no constitution template resolves.
+    """
+    resolver = PresetResolver(project_root)
+    layers = resolver.collect_all_layers("constitution-template", "template")
+    if not layers:
+        return None
+
+    top_layer = layers[0]
+    if top_layer["strategy"] == "replace":
+        content = top_layer["path"].read_bytes()
+        result = "copied"
+    else:
+        composed_content = resolver.resolve_content("constitution-template", "template")
+        if composed_content is None:
+            return None
+        content = composed_content.encode("utf-8")
+        result = "composed"
+
+    _ensure_safe_shared_directory(project_root, memory_constitution.parent)
+    _write_shared_bytes(project_root, memory_constitution, content)
+    provenance = memory_constitution.parent / _CONSTITUTION_PROVENANCE_FILE
+    _write_shared_text(
+        project_root,
+        provenance,
+        json.dumps(
+            {
+                "sha256": _content_sha256(content),
+                "source": top_layer["source"],
+            },
+            indent=2,
+        )
+        + "\n",
+    )
+    return result
 
 
 def _substitute_core_template(
@@ -778,6 +888,7 @@ class PresetManager:
                                         matching_cmds, ext_id, ext_dir,
                                         self.project_root,
                                         context_note=f"\n<!-- Extension: {ext_id} -->\n<!-- Config: .specify/extensions/{ext_id}/ -->\n",
+                                        extension_id=ext_id,
                                     )
                                     registered = True
                             except Exception:
@@ -1199,6 +1310,8 @@ class PresetManager:
                     "command_name": cmd_name,
                     "source_file": source_file,
                     "source": f"extension:{manifest.id}",
+                    "extension_id": manifest.id,
+                    "extension_dir": ext_root,
                 }
                 modern_skill_name, legacy_skill_name = self._skill_names_for_command(cmd_name)
                 restore_index.setdefault(modern_skill_name, restore_info)
@@ -1463,6 +1576,17 @@ class PresetManager:
             if extension_restore:
                 content = extension_restore["source_file"].read_text(encoding="utf-8")
                 frontmatter, body = registrar.parse_frontmatter(content)
+                # Mirror the register-time rewrite (#2101): resolve
+                # extension-relative subdir references (agents/,
+                # knowledge-base/, etc.) to their installed location before
+                # the generic placeholder resolution below, otherwise
+                # restoring after a preset override removal would leave
+                # bare, unresolvable paths in the skill body.
+                body = registrar.rewrite_extension_paths(
+                    body,
+                    extension_restore["extension_id"],
+                    extension_restore["extension_dir"],
+                )
                 if isinstance(selected_ai, str):
                     body = registrar.resolve_skill_placeholders(
                         selected_ai, frontmatter, body, self.project_root
@@ -1615,8 +1739,73 @@ class PresetManager:
                     stacklevel=2,
                 )
 
+        # Seed/re-seed memory/constitution.md from a preset-provided
+        # constitution-template. The constitution is the only template that is
+        # materialized to a live file rather than resolved on demand, so a
+        # preset that ships one (e.g. strategy: replace with a ratified
+        # constitution) must be propagated here. Guard against clobbering an
+        # already-authored constitution by only replacing a file whose recorded
+        # hash (or exact legacy core-template content) proves it was generated.
+        self._seed_constitution_from_preset(manifest, dest_dir)
+
         return manifest
 
+    def _seed_constitution_from_preset(
+        self, manifest: PresetManifest, preset_dir: Path
+    ) -> None:
+        """Seed memory/constitution.md from a preset constitution-template.
+
+        Only runs when the preset declares a ``type: template`` entry named
+        ``constitution-template`` or provides one at a convention path, and the
+        live memory file is either missing or is an unchanged generated file.
+        Authored constitutions are never overwritten.
+        """
+        provides_constitution = any(
+            t.get("type") == "template" and t.get("name") == "constitution-template"
+            for t in manifest.templates
+        ) or any(
+            (preset_dir / relative_path).is_file()
+            for relative_path in (
+                "templates/constitution-template.md",
+                "constitution-template.md",
+            )
+        )
+        if not provides_constitution:
+            return
+
+        self.reconcile_constitution(
+            f"Failed to seed constitution from preset {manifest.id}",
+            create_if_missing=True,
+        )
+
+    def reconcile_constitution(
+        self, failure_context: str, *, create_if_missing: bool = False
+    ) -> None:
+        """Reconcile generated constitution content without failing a persisted change."""
+        try:
+            self._reconcile_constitution(create_if_missing=create_if_missing)
+        except (OSError, UnicodeDecodeError, PresetValidationError, ValueError) as exc:
+            import warnings
+
+            warnings.warn(
+                f"{failure_context}: {exc}.",
+                stacklevel=2,
+            )
+
+    def _reconcile_constitution(self, *, create_if_missing: bool = False) -> None:
+        """Materialize the winning constitution layer when the live file is generated."""
+        memory_constitution = (
+            self.project_root / ".specify" / "memory" / "constitution.md"
+        )
+        if not memory_constitution.exists() and not create_if_missing:
+            return
+        resolver = PresetResolver(self.project_root)
+        if memory_constitution.exists() and not _constitution_is_generated(
+            self.project_root, memory_constitution, resolver
+        ):
+            return
+        _materialize_constitution_template(self.project_root, memory_constitution)
+
     def install_from_zip(
         self,
         zip_path: Path,
@@ -1696,6 +1885,25 @@ class PresetManager:
         # Also include aliases from the manifest as a safety net for registries
         # populated by older versions that may not track aliases.
         removed_cmd_names = set()
+        removed_constitution = any(
+            path.exists()
+            for path in (
+                pack_dir / "templates" / "constitution-template.md",
+                pack_dir / "constitution-template.md",
+            )
+        )
+        if metadata and isinstance(metadata.get("version"), str):
+            memory_constitution = (
+                self.project_root / ".specify" / "memory" / "constitution.md"
+            )
+            removed_constitution = removed_constitution or (
+                _constitution_provenance_matches_preset(
+                    self.project_root,
+                    memory_constitution,
+                    pack_id,
+                    metadata["version"],
+                )
+            )
         for cmd_names in registered_commands.values():
             removed_cmd_names.update(cmd_names)
         manifest_path = pack_dir / "preset.yml"
@@ -1703,6 +1911,11 @@ class PresetManager:
             try:
                 manifest = PresetManifest(manifest_path)
                 for tmpl in manifest.templates:
+                    if (
+                        tmpl.get("type") == "template"
+                        and tmpl.get("name") == "constitution-template"
+                    ):
+                        removed_constitution = True
                     if tmpl.get("type") == "command":
                         for alias in tmpl.get("aliases", []):
                             if isinstance(alias, str):
@@ -1749,6 +1962,18 @@ class PresetManager:
                     stacklevel=2,
                 )
 
+        if removed_constitution:
+            try:
+                self._reconcile_constitution()
+            except (OSError, UnicodeDecodeError, PresetValidationError, ValueError) as exc:
+                import warnings
+
+                warnings.warn(
+                    f"Post-removal constitution reconciliation failed for {pack_id}: "
+                    f"{exc}. The live constitution may be stale.",
+                    stacklevel=2,
+                )
+
         return True
 
     def list_installed(self) -> List[Dict[str, Any]]:
@@ -2574,6 +2799,39 @@ class PresetResolver:
                 self._manifest_cache[key] = None
         return self._manifest_cache[key]
 
+    def _manifest_declared_template(
+        self, pack_dir: Path, template_name: str, template_type: str
+    ) -> tuple[dict | None, Path | None]:
+        """Resolve a preset's manifest-declared template entry and usable file.
+
+        Returns ``(entry, candidate)``:
+        - ``entry`` is the matching ``provides.templates`` mapping, or ``None`` if
+          the manifest is absent or does not list this ``(name, type)``.
+        - ``candidate`` is the declared ``file:`` resolved under ``pack_dir`` IFF
+          it is a regular file (``is_file()``); ``None`` otherwise — a missing,
+          empty, or non-file (e.g. directory) declaration yields ``(entry, None)``.
+
+        The manifest is authoritative: when it declares a template (``entry`` is
+        not ``None``) but the file is unusable (``candidate`` is ``None``),
+        callers must NOT fall back to the convention lookup — that would mask a
+        typo or pick up an undeclared file. Shared by ``resolve()`` and
+        ``collect_all_layers()`` so their manifest-first resolution cannot
+        silently diverge again (the divergence this fix addressed).
+        """
+        manifest = self._get_manifest(pack_dir)
+        if not manifest:
+            return None, None
+        for tmpl in manifest.templates:
+            if tmpl.get("name") == template_name and tmpl.get("type") == template_type:
+                file_path = tmpl.get("file")
+                if file_path:
+                    manifest_candidate = pack_dir / file_path
+                    return tmpl, (
+                        manifest_candidate if manifest_candidate.is_file() else None
+                    )
+                return tmpl, None
+        return None, None
+
     def _get_all_extensions_by_priority(self) -> list[tuple[int, str, dict | None]]:
         """Build unified list of registered and unregistered extensions sorted by priority.
 
@@ -2676,6 +2934,27 @@ class PresetResolver:
             registry = PresetRegistry(self.presets_dir)
             for pack_id, _metadata in registry.list_by_priority():
                 pack_dir = self.presets_dir / pack_id
+                # The preset manifest is authoritative: if it declares this
+                # template with an explicit ``file:``, resolve to that path —
+                # and do NOT fall back to convention when it's missing, to
+                # avoid masking typos or picking up an undeclared file. Only
+                # when the manifest is absent or doesn't list this template do
+                # we use the convention-based subdir lookup. Mirrors
+                # collect_all_layers()/resolve_content() so resolve() and
+                # resolve_with_source() agree with them instead of returning
+                # the core template (or a stray convention file).
+                entry, manifest_candidate = self._manifest_declared_template(
+                    pack_dir, template_name, template_type
+                )
+                if manifest_candidate is not None:
+                    return manifest_candidate
+                if entry is not None:
+                    # Manifest declares this template but the file is missing,
+                    # non-file (e.g. a directory), or an empty/falsey ``file``
+                    # value. The manifest is authoritative, so skip this pack's
+                    # convention fallback rather than mask a typo — mirrors
+                    # collect_all_layers().
+                    continue
                 for subdir in subdirs:
                     if subdir:
                         candidate = pack_dir / subdir / f"{template_name}{ext}"
@@ -2943,31 +3222,22 @@ class PresetResolver:
                 pack_dir = self.presets_dir / pack_id
                 # Read strategy and manifest file path from preset manifest
                 strategy = "replace"
-                manifest_file_path = None
                 manifest_has_strategy = False
-                manifest_found_entry = False
-                manifest = self._get_manifest(pack_dir)
-                if manifest:
-                    for tmpl in manifest.templates:
-                        if (tmpl.get("name") == template_name
-                                and tmpl.get("type") == template_type):
-                            strategy = tmpl.get("strategy", "replace")
-                            manifest_has_strategy = "strategy" in tmpl
-                            manifest_file_path = tmpl.get("file")
-                            manifest_found_entry = True
-                            break
-                # Use manifest file path if specified, otherwise convention-based
-                # lookup — but only when the manifest doesn't exist or doesn't
-                # list this template, so preset.yml stays authoritative.
+                entry, manifest_candidate = self._manifest_declared_template(
+                    pack_dir, template_name, template_type
+                )
+                if entry is not None:
+                    strategy = entry.get("strategy", "replace")
+                    manifest_has_strategy = "strategy" in entry
+                # Use the manifest's declared file when it's a usable regular file;
+                # only fall back to convention-based lookup when the manifest
+                # doesn't list this template at all, so preset.yml stays
+                # authoritative (a declared-but-unusable file skips convention —
+                # parity with resolve()).
                 candidate = None
-                if manifest_file_path:
-                    manifest_candidate = pack_dir / manifest_file_path
-                    if manifest_candidate.exists():
-                        candidate = manifest_candidate
-                    # Explicit file path that doesn't exist: skip convention
-                    # fallback to avoid masking typos or picking up unintended files.
-                elif not manifest_found_entry:
-                    # Manifest doesn't list this template — check convention paths
+                if manifest_candidate is not None:
+                    candidate = manifest_candidate
+                elif entry is None:
                     candidate = _find_in_subdirs(pack_dir)
                 if candidate:
                     # Legacy fallback: if manifest doesn't explicitly declare a
@@ -3038,6 +3308,8 @@ class PresetResolver:
                     "path": candidate,
                     "source": source,
                     "strategy": "replace",
+                    "extension_id": ext_id,
+                    "extension_dir": ext_dir,
                 })
 
         # Priority 4: Core templates (always "replace")
@@ -3157,10 +3429,32 @@ class PresetResolver:
         if not layers:
             return None
 
+        def _read_layer_content(layer: Dict[str, Any]) -> str:
+            """Read a layer's raw text, rewriting extension-relative subdir
+            references (agents/, knowledge-base/, etc.) to their installed
+            location when the layer is extension-provided (#2101).
+
+            Extension layers are always inserted with strategy "replace"
+            (see collect_all_layers), so a layer only ever needs this
+            rewrite when it wins outright above or serves as the
+            composition base below — never as a mid-stack composing
+            (append/prepend/wrap) layer.
+            """
+            text = layer["path"].read_text(encoding="utf-8")
+            extension_id = layer.get("extension_id")
+            extension_dir = layer.get("extension_dir")
+            if extension_id and extension_dir:
+                from ..agents import CommandRegistrar
+
+                text = CommandRegistrar.rewrite_extension_paths(
+                    text, extension_id, extension_dir
+                )
+            return text
+
         # If the top (highest-priority) layer is replace, it wins entirely —
         # lower layers are irrelevant regardless of their strategies.
         if layers[0]["strategy"] == "replace":
-            return layers[0]["path"].read_text(encoding="utf-8")
+            return _read_layer_content(layers[0])
 
         # Composition: build content bottom-up from the effective base.
         # The base is the nearest replace layer scanning from highest priority
@@ -3183,7 +3477,7 @@ class PresetResolver:
 
         # Convert to reversed_layers index
         base_reversed_idx = len(layers) - 1 - base_layer_idx
-        content = layers[base_layer_idx]["path"].read_text(encoding="utf-8")
+        content = _read_layer_content(layers[base_layer_idx])
         # Compose only the layers above the base (higher priority = lower index in layers,
         # higher index in reversed_layers). Process bottom-up from base+1.
         start_idx = base_reversed_idx + 1

src/specify_cli/presets/_commands.py

@@ -469,7 +469,14 @@ def preset_set_priority(
     raw_priority = metadata.get("priority")
     # Only skip if the stored value is already a valid int equal to requested priority
     # This ensures corrupted values (e.g., "high") get repaired even when setting to default (10)
-    if isinstance(raw_priority, int) and raw_priority == priority:
+    # A bool is an int in Python (isinstance(True, int) is True), so exclude it explicitly —
+    # mirroring normalize_priority's bool guard — otherwise a corrupted True/False priority
+    # equals 1/0 here and is never repaired.
+    if (
+        isinstance(raw_priority, int)
+        and not isinstance(raw_priority, bool)
+        and raw_priority == priority
+    ):
         console.print(f"[yellow]Preset '{preset_id}' already has priority {priority}[/yellow]")
         raise typer.Exit(0)
 
@@ -477,6 +484,9 @@ def preset_set_priority(
 
     # Update priority
     manager.registry.update(preset_id, {"priority": priority})
+    manager.reconcile_constitution(
+        f"Failed to reconcile constitution after changing priority for preset {preset_id}"
+    )
 
     console.print(f"[green]✓[/green] Preset '{preset_id}' priority changed: {old_priority} → {priority}")
     console.print("\n[dim]Lower priority = higher precedence in template resolution[/dim]")
@@ -510,6 +520,9 @@ def preset_enable(
 
     # Enable the preset
     manager.registry.update(preset_id, {"enabled": True})
+    manager.reconcile_constitution(
+        f"Failed to reconcile constitution after enabling preset {preset_id}"
+    )
 
     console.print(f"[green]✓[/green] Preset '{preset_id}' enabled")
     console.print("\nTemplates from this preset will now be included in resolution.")
@@ -544,6 +557,9 @@ def preset_disable(
 
     # Disable the preset
     manager.registry.update(preset_id, {"enabled": False})
+    manager.reconcile_constitution(
+        f"Failed to reconcile constitution after disabling preset {preset_id}"
+    )
 
     console.print(f"[green]✓[/green] Preset '{preset_id}' disabled")
     console.print("\nTemplates from this preset will be skipped during resolution.")

src/specify_cli/workflows/base.py

@@ -74,6 +74,9 @@ class StepContext:
     #: Current run ID.
     run_id: str | None = None
 
+    #: Source directory of the workflow definition file.
+    workflow_dir: str | None = None
+
 
 @dataclass
 class StepResult:

src/specify_cli/workflows/catalog.py

@@ -13,6 +13,8 @@ from __future__ import annotations
 import hashlib
 import json
 import os
+import stat
+import tempfile
 import time
 from dataclasses import dataclass
 from pathlib import Path
@@ -71,40 +73,180 @@ class WorkflowRegistry:
         self.registry_path = self.workflows_dir / self.REGISTRY_FILE
         self.data = self._load()
 
+    def _has_symlinked_parent(self) -> bool:
+        """Return True if any directory under .specify/workflows is a symlink."""
+        current = self.project_root
+        for part in (".specify", "workflows"):
+            current = current / part
+            if current.is_symlink():
+                return True
+        return False
+
     def _load(self) -> dict[str, Any]:
         """Load registry from disk or create default."""
+        default_registry: dict[str, Any] = {
+            "schema_version": self.SCHEMA_VERSION,
+            "workflows": {},
+        }
+        # Defense-in-depth: refuse to read through symlinked parents or a
+        # symlinked registry file. Unlike StepRegistry (read-only best-effort
+        # elsewhere), a fabricated empty registry here is not safe: read-only
+        # callers (notably the bundler's remove path) query is_installed()
+        # before ever writing, and would otherwise conclude an installed
+        # workflow is absent, skip removing it, then delete the bundle
+        # record -- leaving the workflow untracked but still on disk. Fail
+        # closed here just like the unreadable-file case below.
+        if self._has_symlinked_parent() or self.registry_path.is_symlink():
+            raise OSError(
+                f"Refusing to read workflow registry at {self.registry_path}: "
+                "a parent directory or the registry file itself is a symlink"
+            )
         if self.registry_path.exists():
             try:
                 with open(self.registry_path, encoding="utf-8") as f:
-                    return json.load(f)
-            except (json.JSONDecodeError, ValueError):
-                # Corrupted registry file — reset to default
-                return {"schema_version": self.SCHEMA_VERSION, "workflows": {}}
-        return {"schema_version": self.SCHEMA_VERSION, "workflows": {}}
+                    data = json.load(f)
+            except OSError as exc:
+                # The real data may still be intact on disk. Fail closed at
+                # construction rather than fabricating an empty registry that
+                # a read-only caller could mistake for "nothing installed."
+                raise OSError(
+                    f"Failed to read workflow registry at {self.registry_path}: {exc}"
+                ) from exc
+            except (
+                json.JSONDecodeError,
+                ValueError,
+                UnicodeError,
+            ) as exc:
+                raise OSError(
+                    f"Workflow registry at {self.registry_path} is corrupted: "
+                    f"{exc}"
+                ) from exc
+            # Validate shape: must be a dict with a dict "workflows" field.
+            if not isinstance(data, dict):
+                raise OSError(
+                    f"Workflow registry at {self.registry_path} is corrupted: "
+                    "top-level value must be an object"
+                )
+            if not isinstance(data.get("workflows"), dict):
+                raise OSError(
+                    f"Workflow registry at {self.registry_path} is corrupted: "
+                    "'workflows' must be an object"
+                )
+            return data
+        return default_registry
 
     def save(self) -> None:
-        """Persist registry to disk."""
+        """Persist registry to disk atomically."""
+        # Refuse to write through symlinked parents (mirrors StepRegistry.save
+        # and the CLI-level _reject_unsafe_dir guard).
+        if self._has_symlinked_parent() or self.registry_path.is_symlink():
+            raise OSError(
+                "Refusing to write workflow registry through a symlinked path."
+            )
         self.workflows_dir.mkdir(parents=True, exist_ok=True)
-        with open(self.registry_path, "w", encoding="utf-8") as f:
-            json.dump(self.data, f, indent=2)
+        # Unique, exclusive temp then replace: a failed dump cannot truncate
+        # the registry, a pre-created symlink cannot redirect the write, and
+        # concurrent CLI processes cannot collide on the same temp path.
+        fd, tmp = tempfile.mkstemp(
+            dir=str(self.registry_path.parent),
+            prefix=f".{self.registry_path.name}.",
+            suffix=".tmp",
+        )
+        try:
+            # Write through a duplicate so the exclusive mkstemp descriptor
+            # stays open for fd-based metadata updates and inode verification.
+            with os.fdopen(os.dup(fd), "w", encoding="utf-8") as f:
+                json.dump(self.data, f, indent=2)
+            # mkstemp creates the temp file at 0600. A pre-existing registry
+            # may be shared more permissively (e.g. 0640/0644); preserve its
+            # mode across the replace so a save doesn't silently lock other
+            # project users out. A brand-new registry has no prior mode to
+            # preserve, so mkstemp's secure 0600 default stands. Mirrors
+            # _utils.py's atomic_write_json (best-effort; data safety over
+            # metadata preservation).
+            try:
+                if self.registry_path.exists():
+                    existing_stat = self.registry_path.stat(
+                        follow_symlinks=False
+                    )
+                    if stat.S_ISREG(existing_stat.st_mode) and hasattr(
+                        os, "fchmod"
+                    ):
+                        os.fchmod(fd, stat.S_IMODE(existing_stat.st_mode))
+                    if stat.S_ISREG(existing_stat.st_mode) and hasattr(
+                        os, "fchown"
+                    ):
+                        try:
+                            os.fchown(
+                                fd, existing_stat.st_uid, existing_stat.st_gid
+                            )
+                        except PermissionError:
+                            pass
+            except OSError:
+                pass
+            staged_stat = os.stat(tmp, follow_symlinks=False)
+            open_stat = os.fstat(fd)
+            if (
+                not stat.S_ISREG(staged_stat.st_mode)
+                or staged_stat.st_dev != open_stat.st_dev
+                or staged_stat.st_ino != open_stat.st_ino
+            ):
+                raise OSError(
+                    "Refusing to replace workflow registry: "
+                    "staged file changed before commit"
+                )
+            os.close(fd)
+            fd = -1
+            os.replace(tmp, self.registry_path)
+        except BaseException:
+            if fd >= 0:
+                try:
+                    os.close(fd)
+                except OSError:
+                    pass
+            try:
+                os.unlink(tmp)
+            except OSError:
+                pass
+            raise
 
     def add(self, workflow_id: str, metadata: dict[str, Any]) -> None:
         """Add or update an installed workflow entry."""
         from datetime import datetime, timezone
 
-        existing = self.data["workflows"].get(workflow_id, {})
+        raw_existing = self.data["workflows"].get(workflow_id)
+        had_entry = workflow_id in self.data["workflows"]
+        # Corrupted-but-parseable registries may hold non-dict entries.
+        existing = raw_existing if isinstance(raw_existing, dict) else {}
         metadata["installed_at"] = existing.get(
             "installed_at", datetime.now(timezone.utc).isoformat()
         )
         metadata["updated_at"] = datetime.now(timezone.utc).isoformat()
         self.data["workflows"][workflow_id] = metadata
-        self.save()
+        try:
+            self.save()
+        except (OSError, TypeError, ValueError):
+            # Roll back the in-memory mutation so a later successful save
+            # cannot persist metadata for a write that failed.
+            if had_entry:
+                self.data["workflows"][workflow_id] = raw_existing
+            else:
+                del self.data["workflows"][workflow_id]
+            raise
 
     def remove(self, workflow_id: str) -> bool:
         """Remove an installed workflow entry. Returns True if found."""
         if workflow_id in self.data["workflows"]:
+            removed_entry = self.data["workflows"][workflow_id]
             del self.data["workflows"][workflow_id]
-            self.save()
+            try:
+                self.save()
+            except (OSError, TypeError, ValueError):
+                # Roll back the in-memory deletion so a save failure can't
+                # desync this instance from the untouched file on disk,
+                # mirroring add()'s rollback-on-save-failure.
+                self.data["workflows"][workflow_id] = removed_entry
+                raise
             return True
         return False
 
@@ -157,8 +299,20 @@ class WorkflowCatalog:
         """Validate that a catalog URL uses HTTPS (localhost HTTP allowed)."""
         from urllib.parse import urlparse
 
-        parsed = urlparse(url)
-        is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+        # A malformed authority (e.g. an unterminated IPv6 bracket
+        # "https://[::1") makes urlparse / hostname access raise ValueError.
+        # This validator's contract is to raise WorkflowValidationError for a
+        # bad URL, so surface that rather than leaking a raw ValueError past the
+        # command handler (which only catches WorkflowValidationError). Mirrors
+        # specify_cli.catalogs (#3435).
+        try:
+            parsed = urlparse(url)
+            hostname = parsed.hostname
+        except ValueError:
+            raise WorkflowValidationError(
+                f"Catalog URL is malformed: {url}"
+            ) from None
+        is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
         if parsed.scheme != "https" and not (
             parsed.scheme == "http" and is_localhost
         ):
@@ -166,7 +320,7 @@ class WorkflowCatalog:
                 f"Catalog URL must use HTTPS (got {parsed.scheme}://). "
                 "HTTP is only allowed for localhost."
             )
-        if not parsed.hostname:
+        if not hostname:
             raise WorkflowValidationError(
                 "Catalog URL must be a valid URL with a host."
             )
@@ -332,15 +486,26 @@ class WorkflowCatalog:
         from specify_cli.authentication.http import open_url as _open_url
 
         def _validate_catalog_url(url: str) -> None:
-            parsed = urlparse(url)
-            is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+            # A malformed authority (e.g. "https://[::1") makes urlparse /
+            # hostname access raise ValueError; treat it as a refused fetch
+            # rather than leaking a raw ValueError (this also validates the
+            # post-redirect resp.geturl(), so a hostile redirect target cannot
+            # crash the fetch either).
+            try:
+                parsed = urlparse(url)
+                hostname = parsed.hostname
+            except ValueError:
+                raise WorkflowCatalogError(
+                    f"Refusing to fetch catalog from malformed URL: {url}"
+                ) from None
+            is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
             if parsed.scheme != "https" and not (
                 parsed.scheme == "http" and is_localhost
             ):
                 raise WorkflowCatalogError(
                     f"Refusing to fetch catalog from non-HTTPS URL: {url}"
                 )
-            if not parsed.hostname:
+            if not hostname:
                 raise WorkflowCatalogError(
                     f"Refusing to fetch catalog from URL with no hostname: {url}"
                 )
@@ -427,6 +592,7 @@ class WorkflowCatalog:
         self,
         query: str | None = None,
         tag: str | None = None,
+        author: str | None = None,
     ) -> list[dict[str, Any]]:
         """Search workflows across all configured catalogs."""
         merged = self._get_merged_workflows()
@@ -438,9 +604,9 @@ class WorkflowCatalog:
                 q = query.lower()
                 searchable = " ".join(
                     [
-                        wf_data.get("name", ""),
-                        wf_data.get("description", ""),
-                        wf_data.get("id", ""),
+                        str(wf_data.get("name") or ""),
+                        str(wf_data.get("description") or ""),
+                        str(wf_data.get("id") or ""),
                     ]
                 ).lower()
                 if q not in searchable:
@@ -451,6 +617,10 @@ class WorkflowCatalog:
                 normalized_tags = [t.lower() for t in tags if isinstance(t, str)]
                 if tag.lower() not in normalized_tags:
                     continue
+            if author:
+                wf_author = wf_data.get("author", "")
+                if not isinstance(wf_author, str) or wf_author.lower() != author.lower():
+                    continue
             results.append(wf_data)
         return results
 
@@ -774,8 +944,20 @@ class StepCatalog:
         """Validate that a catalog URL uses HTTPS (localhost HTTP allowed)."""
         from urllib.parse import urlparse
 
-        parsed = urlparse(url)
-        is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+        # A malformed authority (e.g. an unterminated IPv6 bracket
+        # "https://[::1") makes urlparse / hostname access raise ValueError.
+        # This validator's contract is to raise StepValidationError for a bad
+        # URL, so surface that rather than leaking a raw ValueError past the
+        # command handler (which only catches StepValidationError). Mirrors
+        # specify_cli.catalogs (#3435).
+        try:
+            parsed = urlparse(url)
+            hostname = parsed.hostname
+        except ValueError:
+            raise StepValidationError(
+                f"Catalog URL is malformed: {url}"
+            ) from None
+        is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
         if parsed.scheme != "https" and not (
             parsed.scheme == "http" and is_localhost
         ):
@@ -783,7 +965,7 @@ class StepCatalog:
                 f"Catalog URL must use HTTPS (got {parsed.scheme}://). "
                 "HTTP is only allowed for localhost."
             )
-        if not parsed.hostname:
+        if not hostname:
             raise StepValidationError(
                 "Catalog URL must be a valid URL with a host."
             )
@@ -949,15 +1131,26 @@ class StepCatalog:
         from specify_cli.authentication.http import open_url as _open_url
 
         def _validate_url(url: str) -> None:
-            parsed = urlparse(url)
-            is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
+            # A malformed authority (e.g. "https://[::1") makes urlparse /
+            # hostname access raise ValueError; treat it as a refused fetch
+            # rather than leaking a raw ValueError (this also validates the
+            # post-redirect resp.geturl(), so a hostile redirect target cannot
+            # crash the fetch either).
+            try:
+                parsed = urlparse(url)
+                hostname = parsed.hostname
+            except ValueError:
+                raise StepCatalogError(
+                    f"Refusing to fetch catalog from malformed URL: {url}"
+                ) from None
+            is_localhost = hostname in ("localhost", "127.0.0.1", "::1")
             if parsed.scheme != "https" and not (
                 parsed.scheme == "http" and is_localhost
             ):
                 raise StepCatalogError(
                     f"Refusing to fetch catalog from non-HTTPS URL: {url}"
                 )
-            if not parsed.hostname:
+            if not hostname:
                 raise StepCatalogError(
                     f"Refusing to fetch catalog from URL with no hostname: {url}"
                 )

src/specify_cli/workflows/engine.py

@@ -129,27 +129,50 @@ def validate_workflow(definition: WorkflowDefinition) -> list[str]:
     errors: list[str] = []
 
     # -- Schema version ---------------------------------------------------
-    if definition.schema_version not in ("1.0", "1"):
+    # str() so an unquoted ``schema_version: 1.0`` (YAML float) is accepted —
+    # rejecting it would print "Unsupported schema_version 1.0. Expected '1.0'."
+    if str(definition.schema_version) != "1.0":
         errors.append(
             f"Unsupported schema_version {definition.schema_version!r}. "
             f"Expected '1.0'."
         )
 
     # -- Top-level fields -------------------------------------------------
-    if not definition.id:
+    # YAML parses unquoted scalars like ``id: 123`` or ``version: 1.0`` as
+    # int/float; check types before regex/string operations so authoring
+    # mistakes surface as validation errors instead of tracebacks. Only
+    # ``None``/empty-string count as missing so falsey non-strings
+    # (``id: 0``, ``name: false``) still get the typed error.
+    if definition.id is None or definition.id == "":
         errors.append("Workflow is missing 'workflow.id'.")
-    elif not _ID_PATTERN.match(definition.id):
+    elif not isinstance(definition.id, str):
+        errors.append(
+            f"'workflow.id' must be a string, got "
+            f"{type(definition.id).__name__} ({definition.id!r})."
+        )
+    elif not _ID_PATTERN.fullmatch(definition.id):
         errors.append(
             f"Workflow ID {definition.id!r} must be lowercase alphanumeric "
             f"with hyphens."
         )
 
-    if not definition.name:
+    if definition.name is None or definition.name == "":
         errors.append("Workflow is missing 'workflow.name'.")
+    elif not isinstance(definition.name, str):
+        errors.append(
+            f"'workflow.name' must be a string, got "
+            f"{type(definition.name).__name__} ({definition.name!r})."
+        )
 
-    if not definition.version:
+    if definition.version is None or definition.version == "":
         errors.append("Workflow is missing 'workflow.version'.")
-    elif not re.match(r"^\d+\.\d+\.\d+$", definition.version):
+    elif not isinstance(definition.version, str):
+        errors.append(
+            f"'workflow.version' must be a string, got "
+            f"{type(definition.version).__name__} ({definition.version!r}) — "
+            f'quote it in YAML (version: "1.0.0").'
+        )
+    elif not re.fullmatch(r"\d+\.\d+\.\d+", definition.version):
         errors.append(
             f"Workflow version {definition.version!r} is not valid "
             f"semantic versioning (expected X.Y.Z)."
@@ -256,9 +279,15 @@ def _validate_steps(
             continue
 
         step_id = step_config.get("id")
-        if not step_id:
+        if step_id is None or step_id == "":
             errors.append("Step is missing 'id' field.")
             continue
+        if not isinstance(step_id, str):
+            errors.append(
+                f"Step ID must be a string, got "
+                f"{type(step_id).__name__} ({step_id!r})."
+            )
+            continue
 
         if ":" in step_id:
             errors.append(
@@ -387,18 +416,57 @@ class RunState:
         ID into a path so a malicious value cannot probe or read files
         outside ``.specify/workflows/runs/<run_id>/``.
         """
-        if not isinstance(run_id, str) or not cls._RUN_ID_PATTERN.match(run_id):
+        if not isinstance(run_id, str) or not cls._RUN_ID_PATTERN.fullmatch(run_id):
             raise ValueError(
                 f"Invalid run_id {run_id!r}: must be alphanumeric with "
                 "hyphens/underscores only (and must start with an "
                 "alphanumeric character)."
             )
 
+    @staticmethod
+    def _validate_installed_origin(
+        installed_workflow_id: str | None,
+        installed_registry_root: str | None,
+    ) -> None:
+        """Validate persisted installed-workflow ownership metadata."""
+        if installed_workflow_id is not None:
+            if not isinstance(installed_workflow_id, str):
+                raise ValueError(
+                    "Invalid run state: 'installed_workflow_id' must be a "
+                    f"string or null, got {type(installed_workflow_id).__name__}"
+                )
+            if not _ID_PATTERN.fullmatch(installed_workflow_id):
+                raise ValueError(
+                    "Invalid run state: 'installed_workflow_id' must be a "
+                    "lowercase alphanumeric workflow ID with hyphens"
+                )
+        if installed_registry_root is not None:
+            if not isinstance(installed_registry_root, str):
+                raise ValueError(
+                    "Invalid run state: 'installed_registry_root' must be a "
+                    f"string or null, got {type(installed_registry_root).__name__}"
+                )
+            if not installed_registry_root or not Path(
+                installed_registry_root
+            ).is_absolute():
+                raise ValueError(
+                    "Invalid run state: 'installed_registry_root' must be "
+                    "an absolute path or null"
+                )
+            if installed_workflow_id is None:
+                raise ValueError(
+                    "Invalid run state: 'installed_registry_root' requires "
+                    "'installed_workflow_id'"
+                )
+
     def __init__(
         self,
         run_id: str | None = None,
         workflow_id: str = "",
         project_root: Path | None = None,
+        installed_workflow_id: str | None = None,
+        installed_registry_root: str | None = None,
+        installed_origin_tracked: bool = True,
     ) -> None:
         # ``run_id is None`` (omitted) → auto-generate. An explicit empty
         # string is *not* the same as "omitted" and must be validated like
@@ -410,8 +478,22 @@ class RunState:
         else:
             self.run_id = run_id
         self._validate_run_id(self.run_id)
+        self._validate_installed_origin(
+            installed_workflow_id, installed_registry_root
+        )
         self.workflow_id = workflow_id
         self.project_root = project_root or Path(".")
+        # Identifies the installed workflow (if any) this run was started
+        # from, and the project root that owns its registry — set by
+        # execute() when the source was resolved to an installed ID (see
+        # workflow_run's ownership mapping). None for a direct/non-installed
+        # YAML source. ``installed_origin_tracked`` distinguishes those
+        # explicit None values from legacy state files that predate both
+        # fields, allowing the CLI to conservatively infer same-project
+        # registry ownership before resuming.
+        self.installed_workflow_id = installed_workflow_id
+        self.installed_registry_root = installed_registry_root
+        self.installed_origin_tracked = installed_origin_tracked
         self.status = RunStatus.CREATED
         self.current_step_index = 0
         self.current_step_id: str | None = None
@@ -426,6 +508,7 @@ class RunState:
         # append_log is never called while _lock is held, the two never nest.
         self._log_lock = threading.Lock()
         self.inputs: dict[str, Any] = {}
+        self.workflow_dir: str | None = None
         self.created_at = datetime.now(timezone.utc).isoformat()
         self.updated_at = self.created_at
         self.log_entries: list[dict[str, Any]] = []
@@ -474,10 +557,13 @@ class RunState:
             state_data = {
                 "run_id": self.run_id,
                 "workflow_id": self.workflow_id,
+                "installed_workflow_id": self.installed_workflow_id,
+                "installed_registry_root": self.installed_registry_root,
                 "status": self.status.value,
                 "current_step_index": self.current_step_index,
                 "current_step_id": self.current_step_id,
                 "step_results": self.step_results,
+                "workflow_dir": self.workflow_dir,
                 "created_at": self.created_at,
                 "updated_at": self.updated_at,
             }
@@ -525,16 +611,52 @@ class RunState:
 
         with open(state_path, encoding="utf-8") as f:
             state_data = json.load(f)
+        if not isinstance(state_data, dict):
+            raise ValueError("Invalid run state: expected a JSON object")
+        missing_fields = [
+            field
+            for field in ("run_id", "workflow_id", "status")
+            if field not in state_data
+        ]
+        if missing_fields:
+            raise ValueError(
+                "Invalid run state: missing required field(s): "
+                + ", ".join(missing_fields)
+            )
+
+        workflow_id = state_data["workflow_id"]
+        if not isinstance(workflow_id, str) or not _ID_PATTERN.fullmatch(
+            workflow_id
+        ):
+            raise ValueError(
+                "Invalid run state: 'workflow_id' must be a lowercase "
+                "alphanumeric workflow ID with hyphens"
+            )
+
+        has_installed_workflow_id = "installed_workflow_id" in state_data
+        has_installed_registry_root = "installed_registry_root" in state_data
+        if has_installed_workflow_id != has_installed_registry_root:
+            raise ValueError(
+                "Invalid run state: installed workflow origin fields must "
+                "either both be present or both be absent"
+            )
+
+        installed_workflow_id = state_data.get("installed_workflow_id")
+        installed_registry_root = state_data.get("installed_registry_root")
 
         state = cls(
             run_id=state_data["run_id"],
-            workflow_id=state_data["workflow_id"],
+            workflow_id=workflow_id,
             project_root=project_root,
+            installed_workflow_id=installed_workflow_id,
+            installed_registry_root=installed_registry_root,
+            installed_origin_tracked=has_installed_workflow_id,
         )
         state.status = RunStatus(state_data["status"])
         state.current_step_index = state_data.get("current_step_index", 0)
         state.current_step_id = state_data.get("current_step_id")
         state.step_results = state_data.get("step_results", {})
+        state.workflow_dir = state_data.get("workflow_dir")
         state.created_at = state_data.get("created_at", "")
         state.updated_at = state_data.get("updated_at", "")
 
@@ -542,7 +664,16 @@ class RunState:
         if inputs_path.exists():
             with open(inputs_path, encoding="utf-8") as f:
                 inputs_data = json.load(f)
-            state.inputs = inputs_data.get("inputs", {})
+            if not isinstance(inputs_data, dict):
+                raise ValueError(
+                    "Invalid run inputs: expected a JSON object"
+                )
+            inputs = inputs_data.get("inputs", {})
+            if not isinstance(inputs, dict):
+                raise ValueError(
+                    "Invalid run inputs: 'inputs' must be a JSON object"
+                )
+            state.inputs = inputs
 
         return state
 
@@ -625,6 +756,8 @@ class WorkflowEngine:
         definition: WorkflowDefinition,
         inputs: dict[str, Any] | None = None,
         run_id: str | None = None,
+        installed_workflow_id: str | None = None,
+        installed_registry_root: Path | None = None,
     ) -> RunState:
         """Execute a workflow definition.
 
@@ -636,6 +769,12 @@ class WorkflowEngine:
             User-provided input values.
         run_id:
             Optional run ID (uses SPECKIT_WORKFLOW_RUN_ID when set, otherwise auto-generated).
+        installed_workflow_id, installed_registry_root:
+            When the run was started from an installed workflow (as opposed
+            to a direct/non-installed YAML source), identifies it and its
+            owning registry root so a later ``resume`` can re-check the
+            registry's current disabled state before continuing — see
+            ``workflow_resume``.
 
         Returns
         -------
@@ -653,6 +792,12 @@ class WorkflowEngine:
             run_id=effective_run_id,
             workflow_id=definition.id,
             project_root=self.project_root,
+            installed_workflow_id=installed_workflow_id,
+            installed_registry_root=(
+                str(installed_registry_root)
+                if installed_registry_root is not None
+                else None
+            ),
         )
 
         # Persist a copy of the workflow definition so resume can
@@ -668,6 +813,12 @@ class WorkflowEngine:
         # Resolve inputs
         resolved_inputs = self._resolve_inputs(definition, inputs or {})
         state.inputs = resolved_inputs
+        workflow_dir = (
+            str(definition.source_path.resolve().parent)
+            if definition.source_path is not None
+            else None
+        )
+        state.workflow_dir = workflow_dir
         state.status = RunStatus.RUNNING
         state.save()
 
@@ -678,6 +829,7 @@ class WorkflowEngine:
             default_options=definition.default_options,
             project_root=str(self.project_root),
             run_id=state.run_id,
+            workflow_dir=workflow_dir,
         )
 
         # Execute steps
@@ -743,6 +895,7 @@ class WorkflowEngine:
             default_options=definition.default_options,
             project_root=str(self.project_root),
             run_id=state.run_id,
+            workflow_dir=state.workflow_dir,
         )
 
         from . import STEP_REGISTRY
@@ -953,7 +1106,16 @@ class WorkflowEngine:
                     from .expressions import evaluate_condition
 
                     max_iters = step_config.get("max_iterations")
-                    if not isinstance(max_iters, int) or max_iters < 1:
+                    # A bool is an int in Python (isinstance(True, int) is True
+                    # and True == 1), so a bool max_iterations would slip past
+                    # the int check and cap the loop at range(0)==1 iteration
+                    # instead of the default. Exclude bools, mirroring the
+                    # while/do-while validators and the continue_on_error guard.
+                    if (
+                        isinstance(max_iters, bool)
+                        or not isinstance(max_iters, int)
+                        or max_iters < 1
+                    ):
                         max_iters = 10
                     condition = step_config.get("condition", False)
                     for _loop_iter in range(max_iters - 1):
@@ -1046,9 +1208,9 @@ class WorkflowEngine:
         already flipped), so the prefix never drops the actual halting item.
 
         ``max_concurrency`` is coerced with ``int()``; a value that cannot be
-        coerced (``None``, a non-numeric string, …) or that coerces to <= 1 runs
-        sequentially, while a numeric string like ``"4"`` or a float like ``4.0``
-        is honored.
+        coerced (``None``, a non-numeric string, ``.inf``/``.nan``, …) or that
+        coerces to <= 1 runs sequentially, while a numeric string like ``"4"`` or
+        a float like ``4.0`` is honored.
         """
         if not items:
             return []
@@ -1056,7 +1218,9 @@ class WorkflowEngine:
         halting = (RunStatus.PAUSED, RunStatus.FAILED, RunStatus.ABORTED)
         try:
             workers = max(1, int(max_concurrency))
-        except (TypeError, ValueError):
+        except (TypeError, ValueError, OverflowError):
+            # OverflowError: int(float("inf")) — a YAML ``max_concurrency: .inf``
+            # would otherwise crash the whole run instead of falling back.
             workers = 1
         # Never spin up more workers than there is work — bounds a user-controlled
         # max_concurrency from over-allocating threads.

src/specify_cli/workflows/expressions.py

@@ -35,14 +35,38 @@ def _filter_default(value: Any, default_value: Any = "") -> Any:
 
 
 def _filter_join(value: Any, separator: str = ", ") -> str:
-    """Join a list into a string with *separator*."""
+    """Join a list into a string with *separator*.
+
+    Raises ``ValueError`` when *separator* is not a string. Without the guard a
+    non-string separator (an authoring mistake like ``| join(5)``) reaches
+    ``str.join`` and raises a cryptic ``AttributeError: 'int' object has no
+    attribute 'join'`` that escapes the evaluator and crashes the whole run,
+    since the engine wraps neither expression evaluation nor ``execute`` in a
+    try/except. Mirrors the strict argument handling in ``from_json``.
+    """
+    if not isinstance(separator, str):
+        raise ValueError(
+            f"join: expected a string separator, got {type(separator).__name__}"
+        )
     if isinstance(value, list):
         return separator.join(str(v) for v in value)
     return str(value)
 
 
 def _filter_map(value: Any, attr: str) -> list[Any]:
-    """Map a list of dicts to a specific attribute."""
+    """Map a list of dicts to a specific attribute.
+
+    Raises ``ValueError`` when *attr* is not a string. Without the guard a
+    non-string attribute (an authoring mistake like ``| map(5)``) reaches
+    ``attr.split(".")`` and raises a cryptic ``AttributeError: 'int' object has
+    no attribute 'split'`` that escapes the evaluator and crashes the whole run,
+    since the engine wraps neither expression evaluation nor ``execute`` in a
+    try/except. Mirrors the strict argument handling in ``from_json``.
+    """
+    if not isinstance(attr, str):
+        raise ValueError(
+            f"map: expected a string attribute name, got {type(attr).__name__}"
+        )
     if isinstance(value, list):
         result = []
         for item in value:
@@ -63,9 +87,25 @@ def _filter_map(value: Any, attr: str) -> list[Any]:
     return []
 
 
-def _filter_contains(value: Any, substring: str) -> bool:
-    """Check if a string or list contains *substring*."""
+def _filter_contains(value: Any, substring: Any) -> bool:
+    """Check if a string or list contains *substring*.
+
+    For a string *value*, *substring* must itself be a string: ``x in y`` on a
+    string requires a string left operand, so a non-string argument (an
+    authoring mistake like ``| contains(5)``) would otherwise raise a cryptic
+    ``TypeError`` that escapes the evaluator and crashes the whole run, since
+    the engine wraps neither expression evaluation nor ``execute`` in a
+    try/except. Raise a ``ValueError`` naming the problem instead, mirroring the
+    strict argument handling in ``from_json``. For a list *value*, membership of
+    any element type is legitimate (``5 in [1, 2, 5]``), so that branch is left
+    unguarded.
+    """
     if isinstance(value, str):
+        if not isinstance(substring, str):
+            raise ValueError(
+                "contains: expected a string argument when the value is a "
+                f"string, got {type(substring).__name__}"
+            )
         return substring in value
     if isinstance(value, list):
         return substring in value
@@ -142,7 +182,8 @@ def _build_namespace(context: Any) -> dict[str, Any]:
     # runs use an 8-character uuid4 hex; operator-supplied ids may be
     # any alphanumeric string with hyphens or underscores.
     run_id = getattr(context, "run_id", None) or ""
-    ns["context"] = {"run_id": run_id}
+    workflow_dir = getattr(context, "workflow_dir", None) or ""
+    ns["context"] = {"run_id": run_id, "workflow_dir": workflow_dir}
     return ns
 
 
@@ -464,9 +505,9 @@ def _evaluate_simple_expression(expr: str, namespace: dict[str, Any]) -> Any:
             if op == "<=":
                 return _safe_compare(left, right, "<=")
             if op == " in ":
-                return left in right if right is not None else False
+                return _safe_membership(left, right, negate=False)
             if op == " not in ":
-                return left not in right if right is not None else True
+                return _safe_membership(left, right, negate=True)
 
     # Numeric literal
     try:
@@ -511,6 +552,26 @@ def _coerce_number(value: Any) -> Any:
     return value
 
 
+def _safe_membership(left: Any, right: Any, *, negate: bool) -> bool:
+    """Safely evaluate ``left in right`` (or ``not in``) without crashing.
+
+    ``left in right`` raises ``TypeError`` whenever the operands don't support
+    membership testing — most commonly a non-iterable right operand (``None``,
+    an int, a bool), but also cases like an unhashable ``left`` against a set.
+    In every such case the membership relation is undefined, so treat it as
+    ``False`` (``not in`` as ``True``) rather than leaking the error out of the
+    evaluator and crashing the whole workflow. Mirrors the graceful
+    ``TypeError`` handling in ``_safe_compare`` for the ordering operators, and
+    generalizes the previous ``right is not None`` guard to any operand pair
+    that can't be membership-tested.
+    """
+    try:
+        contained = left in right
+    except TypeError:
+        contained = False
+    return not contained if negate else contained
+
+
 def _safe_compare(left: Any, right: Any, op: str) -> bool:
     """Compare two values for ordering, coercing numeric strings when possible.
 

src/specify_cli/workflows/steps/command/__init__.py

@@ -31,6 +31,20 @@ class CommandStep(StepBase):
     def execute(self, config: dict[str, Any], context: StepContext) -> StepResult:
         command = config.get("command", "")
         input_data = config.get("input", {})
+        # validate() rejects a non-mapping input, but the engine does not
+        # auto-validate before execute(); a workflow that skipped validation can
+        # still reach here. Fail the step with the same contract error rather
+        # than silently coercing to {} and dispatching with empty args — that
+        # would change the command's meaning, hide the config error, and report
+        # COMPLETED, defeating the per-step FAILED / continue_on_error behavior.
+        if not isinstance(input_data, dict):
+            return StepResult(
+                status=StepStatus.FAILED,
+                error=(
+                    f"Command step {config.get('id', '?')!r}: 'input' must be a "
+                    f"mapping, got {type(input_data).__name__}."
+                ),
+            )
 
         # Resolve expressions in input
         resolved_input: dict[str, Any] = {}
@@ -50,8 +64,18 @@ class CommandStep(StepBase):
         # Merge options (workflow defaults ← step overrides)
         options = dict(context.default_options)
         step_options = config.get("options", {})
-        if step_options:
-            options.update(step_options)
+        # Same rationale as 'input': a malformed options fails the step rather
+        # than being silently ignored (which would let an invalid step run and
+        # apparently complete).
+        if not isinstance(step_options, dict):
+            return StepResult(
+                status=StepStatus.FAILED,
+                error=(
+                    f"Command step {config.get('id', '?')!r}: 'options' must be a "
+                    f"mapping, got {type(step_options).__name__}."
+                ),
+            )
+        options.update(step_options)
 
         # Attempt CLI dispatch
         args_str = str(resolved_input.get("args", ""))
@@ -155,4 +179,16 @@ class CommandStep(StepBase):
             errors.append(
                 f"Command step {config.get('id', '?')!r} is missing 'command' field."
             )
+        # execute() iterates input.items() and options.update(step_options); a
+        # non-mapping here would raise at run time. Validate the shape like the
+        # sibling steps (switch 'cases', fan-out 'step') so it is reported, not
+        # crashed on.
+        if "input" in config and not isinstance(config["input"], dict):
+            errors.append(
+                f"Command step {config.get('id', '?')!r}: 'input' must be a mapping."
+            )
+        if "options" in config and not isinstance(config["options"], dict):
+            errors.append(
+                f"Command step {config.get('id', '?')!r}: 'options' must be a mapping."
+            )
         return errors

src/specify_cli/workflows/steps/do_while/__init__.py

@@ -27,6 +27,30 @@ class DoWhileStep(StepBase):
         nested_steps = config.get("steps", [])
         condition = config.get("condition", "false")
 
+        # The engine does not auto-validate step config (see
+        # ``WorkflowEngine.load_workflow``) and feeds ``next_steps`` straight
+        # into ``_execute_steps``, which iterates them as step mappings. A
+        # non-list ``steps`` (a single mapping or scalar authoring mistake)
+        # would otherwise be iterated element-wise — a dict yields its string
+        # keys, a str its characters — and crash the whole run with
+        # AttributeError on ``.get()``. ``validate`` already rejects a non-list
+        # ``steps``; fail this step loudly on an unvalidated run instead,
+        # mirroring the if/switch/fan-out steps. The body always runs on the
+        # first call, so unlike the while step this guard is unconditional.
+        if not isinstance(nested_steps, list):
+            return StepResult(
+                status=StepStatus.FAILED,
+                output={
+                    "condition": condition,
+                    "max_iterations": max_iterations,
+                    "loop_type": "do-while",
+                },
+                error=(
+                    f"Do-while step {config.get('id', '?')!r}: 'steps' must be "
+                    f"a list of steps, got {type(nested_steps).__name__}."
+                ),
+            )
+
         # Always execute body at least once; the engine layer evaluates
         # `condition` after each iteration to decide whether to loop.
         return StepResult(

src/specify_cli/workflows/steps/fan_in/__init__.py

@@ -24,6 +24,24 @@ class FanInStep(StepBase):
         if not isinstance(output_config, dict):
             output_config = {}
 
+        # The engine does not auto-validate step config, so an unvalidated run
+        # with a non-list ``wait_for`` reaches here raw. Iterating it then
+        # either crashes the whole run (a scalar like an int or None raises
+        # TypeError) or, worse, silently iterates a string's characters and
+        # yields a bogus join of empty results with a COMPLETED status — the
+        # exact "silent empty result + COMPLETED" wiring bug the engine's
+        # fan-in validation guards against. Fail this step loudly instead,
+        # mirroring the fan-out step's non-list ``items`` handling.
+        if not isinstance(wait_for, list):
+            return StepResult(
+                status=StepStatus.FAILED,
+                error=(
+                    f"Fan-in step {config.get('id', '?')!r}: 'wait_for' must be "
+                    f"a list of step IDs, got {type(wait_for).__name__}."
+                ),
+                output={"results": []},
+            )
+
         # Collect results from referenced steps
         results = []
         for step_id in wait_for:

src/specify_cli/workflows/steps/if_then/__init__.py

@@ -47,8 +47,8 @@ class IfThenStep(StepBase):
             errors.append(
                 f"If step {config.get('id', '?')!r}: 'then' must be a list of steps."
             )
-        else_branch = config.get("else", [])
-        if else_branch and not isinstance(else_branch, list):
+        else_branch = config.get("else")
+        if else_branch is not None and not isinstance(else_branch, list):
             errors.append(
                 f"If step {config.get('id', '?')!r}: 'else' must be a list of steps."
             )

src/specify_cli/workflows/steps/shell/__init__.py

@@ -3,6 +3,8 @@
 from __future__ import annotations
 
 import json
+import math
+import os
 import subprocess
 from typing import Any
 
@@ -25,14 +27,26 @@ class ShellStep(StepBase):
         run_cmd = str(run_cmd)
 
         cwd = context.project_root or "."
-        # Defensive: the engine does not auto-validate step config, so an
-        # invalid ``timeout`` (string, None, ...) would otherwise raise a
-        # TypeError from subprocess.run() and crash the whole run.  Mirror
-        # the engine's handling of unvalidated ``continue_on_error`` by
-        # only honoring well-formed values and falling back to the default.
+        # Per-step execution timeout in seconds; defaults to 300 for backward
+        # compatibility. The engine does not auto-validate step config, so
+        # validate here as well — a caller that skips WorkflowEngine.validate()
+        # must fail the step cleanly rather than crash subprocess.run() with a
+        # TypeError (or silently coerce ``timeout: true`` to a 1s duration,
+        # since bool is an int subclass).
         timeout = config.get("timeout", 300)
-        if isinstance(timeout, bool) or not isinstance(timeout, int) or timeout <= 0:
-            timeout = 300
+        timeout_error = self._timeout_error(config)
+        if timeout_error is not None:
+            return StepResult(
+                status=StepStatus.FAILED,
+                error=timeout_error,
+                output={"exit_code": -1, "stdout": "", "stderr": "invalid timeout"},
+            )
+
+        env = {**os.environ}
+        if context.workflow_dir:
+            env["SPECKIT_WORKFLOW_DIR"] = context.workflow_dir
+        else:
+            env.pop("SPECKIT_WORKFLOW_DIR", None)
 
         # NOTE: shell=True is required to support pipes, redirects, and
         # multi-command expressions in workflow YAML.  Workflow authors
@@ -45,6 +59,7 @@ class ShellStep(StepBase):
                 capture_output=True,
                 text=True,
                 cwd=cwd,
+                env=env,
                 timeout=timeout,
             )
             output = {
@@ -92,6 +107,32 @@ class ShellStep(StepBase):
                 output={"exit_code": -1, "stdout": "", "stderr": str(exc)},
             )
 
+    @staticmethod
+    def _timeout_error(config: dict[str, Any]) -> str | None:
+        """Return an error message if ``config['timeout']`` is invalid, else None.
+
+        Shared by execute() and validate() so both paths reject the same
+        values with the same message. An absent ``timeout`` is valid (the
+        default is used). bool is a subclass of int, but ``timeout: true`` is a
+        config error rather than a duration, so it is rejected explicitly.
+        Non-finite floats (YAML ``.inf``/``.nan``) pass a plain ``> 0`` check
+        but would raise in subprocess.run(), so they are rejected too.
+        """
+        if "timeout" not in config:
+            return None
+        timeout = config["timeout"]
+        if (
+            isinstance(timeout, bool)
+            or not isinstance(timeout, (int, float))
+            or not math.isfinite(timeout)
+            or timeout <= 0
+        ):
+            return (
+                f"Shell step {config.get('id', '?')!r}: 'timeout' must be a "
+                f"positive number of seconds, got {timeout!r}."
+            )
+        return None
+
     def validate(self, config: dict[str, Any]) -> list[str]:
         errors = super().validate(config)
         if "run" not in config:
@@ -114,16 +155,7 @@ class ShellStep(StepBase):
                 f"Shell step {config.get('id', '?')!r}: 'output_format' must "
                 f"be 'json' when present, got {output_format!r}."
             )
-        if "timeout" in config:
-            timeout = config["timeout"]
-            # bool is an int subclass, so reject it explicitly.
-            if (
-                isinstance(timeout, bool)
-                or not isinstance(timeout, int)
-                or timeout <= 0
-            ):
-                errors.append(
-                    f"Shell step {config.get('id', '?')!r}: 'timeout' must be a "
-                    f"positive integer (seconds) when present, got {timeout!r}."
-                )
+        timeout_error = self._timeout_error(config)
+        if timeout_error is not None:
+            errors.append(timeout_error)
         return errors

src/specify_cli/workflows/steps/switch/__init__.py

@@ -26,6 +26,20 @@ class SwitchStep(StepBase):
         str_value = str(value) if value is not None else ""
 
         cases = config.get("cases", {})
+        if not isinstance(cases, dict):
+            # The engine does not auto-validate step config, so an unvalidated
+            # run with a non-mapping ``cases`` (a list/scalar authoring mistake)
+            # would otherwise raise AttributeError from ``.items()`` below and
+            # crash the whole run. Fail this step loudly instead, mirroring the
+            # fan-out step's non-list ``items`` handling.
+            return StepResult(
+                status=StepStatus.FAILED,
+                error=(
+                    f"Switch step {config.get('id', '?')!r}: 'cases' must be a "
+                    f"mapping, got {type(cases).__name__}."
+                ),
+                output={"matched_case": None, "expression_value": value},
+            )
         for case_key, case_steps in cases.items():
             if str(case_key) == str_value:
                 return StepResult(

src/specify_cli/workflows/steps/while_loop/__init__.py

@@ -26,6 +26,32 @@ class WhileStep(StepBase):
         nested_steps = config.get("steps", [])
 
         result = evaluate_condition(condition, context)
+
+        # The engine does not auto-validate step config (see
+        # ``WorkflowEngine.load_workflow``) and feeds ``next_steps`` straight
+        # into ``_execute_steps``, which iterates them as step mappings. A
+        # non-list ``steps`` (a single mapping or scalar authoring mistake)
+        # would otherwise be iterated element-wise — a dict yields its string
+        # keys, a str its characters — and crash the whole run with
+        # AttributeError on ``.get()``. ``validate`` already rejects a non-list
+        # ``steps``; fail this step loudly on an unvalidated run instead,
+        # mirroring the if/switch/fan-out steps. The guard fires only when the
+        # body would actually be dispatched (condition truthy). The condition is
+        # still evaluated first, so its result is surfaced for downstream context.
+        if result and not isinstance(nested_steps, list):
+            return StepResult(
+                status=StepStatus.FAILED,
+                output={
+                    "condition_result": True,
+                    "max_iterations": max_iterations,
+                    "loop_type": "while",
+                },
+                error=(
+                    f"While step {config.get('id', '?')!r}: 'steps' must be a "
+                    f"list of steps, got {type(nested_steps).__name__}."
+                ),
+            )
+
         if result:
             return StepResult(
                 status=StepStatus.COMPLETED,

templates/checklist-template.md

@@ -6,16 +6,16 @@
 
 **Note**: This checklist is generated by the `__SPECKIT_COMMAND_CHECKLIST__` command based on feature context and requirements.
 
-<!-- 
+<!--
   ============================================================================
   IMPORTANT: The checklist items below are SAMPLE ITEMS for illustration only.
-  
+
   The __SPECKIT_COMMAND_CHECKLIST__ command MUST replace these with actual items based on:
   - User's specific checklist request
   - Feature requirements from spec.md
   - Technical context from plan.md
   - Implementation details from tasks.md
-  
+
   DO NOT keep these sample items in the generated checklist file.
   ============================================================================
 -->

templates/commands/clarify.md

@@ -1,6 +1,6 @@
 ---
 description: Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
-handoffs: 
+handoffs:
   - label: Build Technical Plan
     agent: speckit.plan
     prompt: Create a plan for the spec. I am building with...

templates/commands/constitution.md

@@ -1,6 +1,6 @@
 ---
 description: Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
-handoffs: 
+handoffs:
   - label: Build Specification
     agent: speckit.specify
     prompt: Implement the feature specification based on the updated constitution. I want to build...
@@ -81,7 +81,7 @@ Follow this execution flow:
    - Read `.specify/templates/plan-template.md` and ensure any "Constitution Check" or rules align with updated principles.
    - Read `.specify/templates/spec-template.md` for scope/requirements alignment—update if constitution adds/removes mandatory sections or constraints.
    - Read `.specify/templates/tasks-template.md` and ensure task categorization reflects new or removed principle-driven task types (e.g., observability, versioning, testing discipline).
-   - Read each command file in `.specify/templates/commands/*.md` (including this one) to verify no outdated references (agent-specific names like CLAUDE only) remain when generic guidance is required.
+   - Read each installed Spec Kit command file for your agent (including this one) — named `speckit.*` or `speckit-*` (dot or hyphen depending on the agent), or laid out as `speckit-<name>/SKILL.md` for skills-based integrations, e.g. in `.github/agents/`, `.github/skills/`, `.claude/skills/`, or your agent's equivalent commands directory — to verify no outdated references (CLAUDE-only or other agent-specific names) remain when generic guidance is required.
    - Read any runtime guidance docs (e.g., `README.md`, `docs/quickstart.md`, or agent-specific guidance files if present). Update references to principles changed.
 
 5. Produce a Sync Impact Report (prepend as an HTML comment at top of the constitution file after update):

templates/commands/implement.md

@@ -43,7 +43,7 @@ You **MUST** consider the user input before proceeding (if not empty).
     **Automatic Pre-Hook**: {extension}
     Executing: `/{command}`
     EXECUTE_COMMAND: {command}
-    
+
     Wait for the result of the hook command before proceeding to the Outline.
     ```
     After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `/skill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.
@@ -145,7 +145,7 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 6. Execute implementation following the task plan:
    - **Phase-by-phase execution**: Complete each phase before moving to the next
-   - **Respect dependencies**: Run sequential tasks in order, parallel tasks [P] can run together  
+   - **Respect dependencies**: Run sequential tasks in order, parallel tasks [P] can run together
    - **Follow TDD approach**: Execute test tasks before their corresponding implementation tasks
    - **File-based coordination**: Tasks affecting the same files must run sequentially
    - **Validation checkpoints**: Verify each phase completion before proceeding

templates/commands/plan.md

@@ -1,6 +1,6 @@
 ---
 description: Execute the implementation planning workflow using the plan template to generate design artifacts.
-handoffs: 
+handoffs:
   - label: Create Tasks
     agent: speckit.tasks
     prompt: Break the plan into tasks

templates/commands/specify.md

@@ -1,6 +1,6 @@
 ---
 description: Create or update the feature specification from a natural language feature description.
-handoffs: 
+handoffs:
   - label: Build Technical Plan
     agent: speckit.plan
     prompt: Create a plan for the spec. I am building with...
@@ -147,20 +147,20 @@ Given that feature description, do this:
 
       ```markdown
       # Specification Quality Checklist: [FEATURE NAME]
-      
+
       **Purpose**: Validate specification completeness and quality before proceeding to planning
       **Created**: [DATE]
       **Feature**: [Link to spec.md]
-      
+
       ## Content Quality
-      
+
       - [ ] No implementation details (languages, frameworks, APIs)
       - [ ] Focused on user value and business needs
       - [ ] Written for non-technical stakeholders
       - [ ] All mandatory sections completed
-      
+
       ## Requirement Completeness
-      
+
       - [ ] No [NEEDS CLARIFICATION] markers remain
       - [ ] Requirements are testable and unambiguous
       - [ ] Success criteria are measurable
@@ -169,16 +169,16 @@ Given that feature description, do this:
       - [ ] Edge cases are identified
       - [ ] Scope is clearly bounded
       - [ ] Dependencies and assumptions identified
-      
+
       ## Feature Readiness
-      
+
       - [ ] All functional requirements have clear acceptance criteria
       - [ ] User scenarios cover primary flows
       - [ ] Feature meets measurable outcomes defined in Success Criteria
       - [ ] No implementation details leak into specification
-      
+
       ## Notes
-      
+
       - Items marked incomplete require spec updates before `__SPECKIT_COMMAND_CLARIFY__` or `__SPECKIT_COMMAND_PLAN__`
       ```
 
@@ -203,20 +203,20 @@ Given that feature description, do this:
 
            ```markdown
            ## Question [N]: [Topic]
-           
+
            **Context**: [Quote relevant spec section]
-           
+
            **What we need to know**: [Specific question from NEEDS CLARIFICATION marker]
-           
+
            **Suggested Answers**:
-           
+
            | Option | Answer | Implications |
            |--------|--------|--------------|
            | A      | [First suggested answer] | [What this means for the feature] |
            | B      | [Second suggested answer] | [What this means for the feature] |
            | C      | [Third suggested answer] | [What this means for the feature] |
            | Custom | Provide your own answer | [Explain how to provide custom input] |
-           
+
            **Your choice**: _[Wait for user response]_
            ```
 

templates/commands/tasks.md

@@ -1,6 +1,6 @@
 ---
 description: Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
-handoffs: 
+handoffs:
   - label: Analyze For Consistency
     agent: speckit.analyze
     prompt: Run a project analysis for consistency
@@ -51,7 +51,7 @@ You **MUST** consider the user input before proceeding (if not empty).
     **Automatic Pre-Hook**: {extension}
     Executing: `/{command}`
     EXECUTE_COMMAND: {command}
-    
+
     Wait for the result of the hook command before proceeding to the Outline.
     ```
     After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `/skill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.
@@ -161,7 +161,7 @@ Every task MUST strictly follow this format:
 4. **[Story] label**: REQUIRED for user story phase tasks only
    - Format: [US1], [US2], [US3], etc. (maps to user stories from spec.md)
    - Setup phase: NO story label
-   - Foundational phase: NO story label  
+   - Foundational phase: NO story label
    - User Story phases: MUST have story label
    - Polish phase: NO story label
 5. **Description**: Clear action with exact file path

templates/plan-template.md

@@ -4,7 +4,7 @@
 
 **Input**: Feature specification from `/specs/[###-feature-name]/spec.md`
 
-**Note**: This template is filled in by the `__SPECKIT_COMMAND_PLAN__` command. See `.specify/templates/plan-template.md` for the execution workflow.
+**Note**: This template is filled in by the `__SPECKIT_COMMAND_PLAN__` command; its definition describes the execution workflow.
 
 ## Summary
 

templates/vscode-settings.json

@@ -11,4 +11,3 @@
         ".specify/scripts/powershell/": true
     }
 }
-

tests/contract/test_bundle_cli.py

@@ -6,6 +6,7 @@ contracts/cli-commands.md (offline, discovery-only refusal, not-a-project error)
 """
 from __future__ import annotations
 
+import io
 import json
 from pathlib import Path
 from unittest.mock import patch
@@ -63,6 +64,42 @@ def test_commands_outside_project_fail_with_guidance(tmp_path: Path, monkeypatch
     assert "Spec Kit project" in result.output
 
 
+def test_remove_reports_clean_error_when_primitive_raises_raw_exception(
+    project: Path,
+):
+    """A raw exception from a primitive installer (e.g. an OSError from an
+    unreadable workflow registry surfacing through _WorkflowKindManager's
+    fail-closed construction) must not propagate uncaught through
+    `specify bundle remove` -- the command only catches BundlerError, so
+    without a conversion at the remove_bundle boundary this would exit
+    with an unhandled exception and empty/raw output instead of a clean,
+    actionable message, and no removal side effects should occur either."""
+    from specify_cli.bundler.models.manifest import BundleManifest
+    from specify_cli.bundler.models.records import load_records
+    from specify_cli.bundler.services.adapters import DefaultPrimitiveInstaller
+    from specify_cli.bundler.services.installer import install_bundle
+    from specify_cli.bundler.services.resolver import resolve_install_plan
+    from tests.bundler_helpers import FakeInstaller
+
+    manifest = BundleManifest.from_dict(valid_manifest_dict())
+    plan = resolve_install_plan(
+        manifest, speckit_version="0.11.2", active_integration="copilot"
+    )
+    install_bundle(project, plan, FakeInstaller(), manifest=manifest)
+
+    def boom(self, project_root, component):
+        raise OSError("workflow registry unreadable")
+
+    with pytest.MonkeyPatch.context() as mp:
+        mp.setattr(DefaultPrimitiveInstaller, "is_installed", boom)
+        result = runner.invoke(app, ["bundle", "remove", "demo-bundle"])
+
+    assert result.exit_code != 0
+    assert result.output.strip() != ""
+    assert result.exception is None or isinstance(result.exception, SystemExit)
+    assert {r.bundle_id for r in load_records(project)} == {"demo-bundle"}
+
+
 def test_fail_writes_error_to_stderr_not_stdout(capsys):
     """_fail must write to stderr, not stdout: every bundle command routes errors
     through it, and under --json the error would otherwise corrupt the JSON payload
@@ -175,7 +212,23 @@ def test_build_produces_artifact(project: Path):
     assert len(artifacts) == 1
 
 
-def test_info_expands_full_component_set(project: Path):
+def _mock_manifest_download(monkeypatch, source_path: Path) -> None:
+    """Mock the HTTPS manifest fetch to return a locally-authored manifest.
+
+    Catalog ``download_url``s are HTTPS-only, so ``info`` tests can no longer
+    point one at a local file. Patch ``_download_manifest`` to return the
+    manifest parsed from *source_path* (a bundle.yml or a .zip artifact),
+    exercising ``info``'s expansion without a network call.
+    """
+    from specify_cli.commands.bundle import _local_manifest_source
+
+    monkeypatch.setattr(
+        "specify_cli.commands.bundle._download_manifest",
+        lambda resolved, *, offline: _local_manifest_source(str(source_path)),
+    )
+
+
+def test_info_expands_full_component_set(project: Path, monkeypatch):
     bundle_dir = project / "src-bundle"
     bundle_dir.mkdir()
     (bundle_dir / "bundle.yml").write_text(
@@ -183,13 +236,14 @@ def test_info_expands_full_component_set(project: Path):
     )
     catalog = project / "local-catalog.json"
     entry = catalog_entry_dict(
-        "demo-bundle", download_url=str(bundle_dir / "bundle.yml")
+        "demo-bundle", download_url="https://example.com/demo-bundle.zip"
     )
     write_catalog_file(catalog, {"demo-bundle": entry})
     added = runner.invoke(
         app, ["bundle", "catalog", "add", str(catalog), "--id", "local"]
     )
     assert added.exit_code == 0, added.output
+    _mock_manifest_download(monkeypatch, bundle_dir / "bundle.yml")
 
     result = runner.invoke(app, ["bundle", "info", "demo-bundle", "--json", "--offline"])
     assert result.exit_code == 0, result.output
@@ -207,7 +261,7 @@ def test_info_expands_full_component_set(project: Path):
     assert "Trust" in text.output
 
 
-def test_info_expands_discovery_only_bundle(project: Path):
+def test_info_expands_discovery_only_bundle(project: Path, monkeypatch):
     # Discovery-only bundles must still be fully inspectable via `info`;
     # only `install` is refused for them.
     bundle_dir = project / "disc-bundle"
@@ -217,7 +271,7 @@ def test_info_expands_discovery_only_bundle(project: Path):
     )
     catalog = project / "disc-catalog.json"
     entry = catalog_entry_dict(
-        "demo-bundle", download_url=str(bundle_dir / "bundle.yml")
+        "demo-bundle", download_url="https://example.com/demo-bundle.zip"
     )
     write_catalog_file(catalog, {"demo-bundle": entry})
     config = {
@@ -230,6 +284,7 @@ def test_info_expands_discovery_only_bundle(project: Path):
     (project / ".specify" / "bundle-catalogs.yml").write_text(
         yaml.safe_dump(config), encoding="utf-8"
     )
+    _mock_manifest_download(monkeypatch, bundle_dir / "bundle.yml")
     result = runner.invoke(app, ["bundle", "info", "demo-bundle", "--json", "--offline"])
     assert result.exit_code == 0, result.output
     payload = json.loads(result.output)
@@ -237,8 +292,9 @@ def test_info_expands_discovery_only_bundle(project: Path):
     assert ("extensions", "ext-a") in components
 
 
-def test_info_resolves_local_zip_download_url(project: Path):
-    # A local .zip artifact as download_url is extracted to read bundle.yml.
+def test_info_expands_zip_sourced_bundle(project: Path, monkeypatch):
+    # A .zip artifact is extracted to read bundle.yml; info expands it. (The
+    # download itself is HTTPS-only now and mocked here — see contract note.)
     bundle_dir = project / "zip-src"
     bundle_dir.mkdir()
     (bundle_dir / "bundle.yml").write_text(
@@ -249,12 +305,15 @@ def test_info_resolves_local_zip_download_url(project: Path):
     catalog = project / "zip-catalog.json"
     write_catalog_file(
         catalog,
-        {"demo-bundle": catalog_entry_dict("demo-bundle", download_url=str(artifact))},
+        {"demo-bundle": catalog_entry_dict(
+            "demo-bundle", download_url="https://example.com/demo-bundle.zip"
+        )},
     )
     added = runner.invoke(
         app, ["bundle", "catalog", "add", str(catalog), "--id", "local"]
     )
     assert added.exit_code == 0, added.output
+    _mock_manifest_download(monkeypatch, artifact)
     result = runner.invoke(app, ["bundle", "info", "demo-bundle", "--json", "--offline"])
     assert result.exit_code == 0, result.output
     payload = json.loads(result.output)
@@ -410,25 +469,16 @@ def test_install_integration_override_cannot_bypass_clash_guard(project: Path):
 # ===== Private GitHub release asset URL resolution =====
 
 
-class FakeBundleResponse:
+class FakeBundleResponse(io.BytesIO):
     """Minimal context-manager response stub for open_url fakes."""
 
     def __init__(self, data: bytes, url: str = "https://api.github.com/repos/org/repo/releases/assets/99"):
-        self._data = data
+        super().__init__(data)
         self._url = url
 
-    def read(self) -> bytes:
-        return self._data
-
     def geturl(self) -> str:
         return self._url
 
-    def __enter__(self):
-        return self
-
-    def __exit__(self, *_):
-        return False
-
 
 def _make_catalog_config(catalog_path: Path, project: Path) -> None:
     """Write a bundle-catalogs.yml pointing at *catalog_path* in *project*."""

tests/extensions/git/test_git_extension_python_parity.py

@@ -0,0 +1,647 @@
+"""
+Parity tests for the Python port of the git extension scripts (extensions/git/scripts/python/).
+
+Each test runs the bash script and its Python twin in identical twin projects
+and asserts matching output, exit codes, and resulting git state.
+"""
+
+import json
+import os
+import re
+import runpy
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+
+import pytest
+
+from tests.conftest import requires_bash
+from tests.extensions.git.test_git_extension import (
+    _GIT_ENV,
+    _init_git,
+    _run_bash,
+    _setup_project,
+    _write_config,
+)
+
+PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent.parent
+EXT_PY = PROJECT_ROOT / "extensions" / "git" / "scripts" / "python"
+CORE_COMMON_PY = PROJECT_ROOT / "scripts" / "python" / "common.py"
+
+PY_SCRIPTS = {
+    "create-new-feature-branch": "create_new_feature_branch.py",
+    "initialize-repo": "initialize_repo.py",
+    "auto-commit": "auto_commit.py",
+}
+
+
+def _setup_py_project(tmp_path: Path, *, git: bool = True) -> Path:
+    """Twin of _setup_project that also installs the Python scripts."""
+    project = _setup_project(tmp_path, git=git)
+
+    py_core = project / ".specify" / "scripts" / "python"
+    py_core.mkdir(parents=True, exist_ok=True)
+    shutil.copy(CORE_COMMON_PY, py_core / "common.py")
+
+    ext_py = project / ".specify" / "extensions" / "git" / "scripts" / "python"
+    ext_py.mkdir(parents=True, exist_ok=True)
+    for f in EXT_PY.iterdir():
+        if f.suffix == ".py":
+            shutil.copy(f, ext_py / f.name)
+    return project
+
+
+def _run_py(
+    script_name: str,
+    cwd: Path,
+    *args: str,
+    env_extra: dict | None = None,
+    run_cwd: Path | None = None,
+) -> subprocess.CompletedProcess:
+    """Run an extension Python script.
+
+    ``run_cwd`` overrides the working directory while the script path is
+    still resolved against ``cwd``, for tests that invoke a project's script
+    from outside that project.
+    """
+    script = (
+        cwd / ".specify" / "extensions" / "git" / "scripts" / "python" / PY_SCRIPTS[script_name]
+    )
+    env = {**os.environ, **_GIT_ENV, **(env_extra or {})}
+    return subprocess.run(
+        [sys.executable, str(script), *args],
+        cwd=run_cwd or cwd,
+        capture_output=True,
+        text=True,
+        env=env,
+    )
+
+
+def _twin_projects(tmp_path: Path, *, git: bool = True) -> tuple[Path, Path]:
+    """Two identically named projects so {app} tokens match."""
+    bash_proj = _setup_py_project(tmp_path / "bash" / "proj", git=git)
+    py_proj = _setup_py_project(tmp_path / "py" / "proj", git=git)
+    return bash_proj, py_proj
+
+
+def _assert_parity(
+    bash_result: subprocess.CompletedProcess,
+    py_result: subprocess.CompletedProcess,
+    *,
+    stdout: bool = True,
+    stderr: bool = True,
+) -> None:
+    assert py_result.returncode == bash_result.returncode, (
+        f"exit codes diverge: bash={bash_result.returncode} py={py_result.returncode}\n"
+        f"bash stderr: {bash_result.stderr}\npy stderr: {py_result.stderr}"
+    )
+    if stdout:
+        assert py_result.stdout == bash_result.stdout
+    if stderr:
+        py_stderr = py_result.stderr
+        bash_stderr = bash_result.stderr
+        if os.name == "nt":
+            py_stderr = _without_persist_hint(py_stderr)
+            bash_stderr = _without_persist_hint(bash_stderr)
+        assert py_stderr == bash_stderr
+
+
+def _without_persist_hint(stderr: str) -> str:
+    return "".join(
+        line
+        for line in stderr.splitlines(keepends=True)
+        if not line.startswith("# To persist: ")
+    )
+
+
+@requires_bash
+class TestCreateFeatureBranchParity:
+    def test_sequential_branch_json(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "Add user authentication")
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "Add user authentication")
+        _assert_parity(b, p)
+        data = json.loads(p.stdout)
+        assert data == {"BRANCH_NAME": "001-user-authentication", "FEATURE_NUM": "001"}
+        branch = subprocess.run(
+            ["git", "rev-parse", "--abbrev-ref", "HEAD"],
+            cwd=py_proj,
+            capture_output=True,
+            text=True,
+        ).stdout.strip()
+        assert branch == "001-user-authentication"
+
+    def test_slug_generation_stop_words_and_acronyms(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        description = "I want to add DB caching for the API layer"
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "--dry-run", description)
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "--dry-run", description)
+        _assert_parity(b, p)
+
+    def test_short_name_cleaning(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        # Single separator runs only: the bash twin's collapse step
+        # (sed 's/-\+/-/g') is a GNU-ism that BSD sed treats literally.
+        b = _run_bash(
+            "create-new-feature-branch.sh", bash_proj,
+            "--json", "--dry-run", "--short-name", "User_Auth!", "desc",
+        )
+        p = _run_py(
+            "create-new-feature-branch", py_proj,
+            "--json", "--dry-run", "--short-name", "User_Auth!", "desc",
+        )
+        _assert_parity(b, p)
+        assert json.loads(p.stdout)["BRANCH_NAME"] == "001-user-auth"
+
+    def test_numbering_from_specs_and_branches(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            (proj / "specs" / "007-existing").mkdir(parents=True)
+            (proj / "specs" / "20260101-120000-timestamped").mkdir(parents=True)
+            subprocess.run(["git", "branch", "012-in-branch"], cwd=proj, check=True)
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "--dry-run", "next feature")
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "--dry-run", "next feature")
+        _assert_parity(b, p)
+        assert json.loads(p.stdout)["FEATURE_NUM"] == "013"
+
+    def test_explicit_number(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "--number", "42", "some feature")
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "--number", "42", "some feature")
+        _assert_parity(b, p)
+        assert json.loads(p.stdout)["FEATURE_NUM"] == "042"
+
+    def test_timestamp_mode_format(self, tmp_path: Path):
+        _, py_proj = _twin_projects(tmp_path)
+        p = _run_py(
+            "create-new-feature-branch", py_proj,
+            "--json", "--timestamp", "--short-name", "user-auth", "desc",
+        )
+        assert p.returncode == 0
+        data = json.loads(p.stdout)
+        assert re.fullmatch(r"[0-9]{8}-[0-9]{6}", data["FEATURE_NUM"])
+        assert data["BRANCH_NAME"] == f"{data['FEATURE_NUM']}-user-auth"
+
+    def test_timestamp_with_number_warns(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        b = _run_bash(
+            "create-new-feature-branch.sh", bash_proj,
+            "--json", "--dry-run", "--timestamp", "--number", "5", "desc word",
+        )
+        p = _run_py(
+            "create-new-feature-branch", py_proj,
+            "--json", "--dry-run", "--timestamp", "--number", "5", "desc word",
+        )
+        assert p.returncode == b.returncode == 0
+        warning = "[specify] Warning: --number is ignored when --timestamp is used"
+        assert warning in b.stderr
+        assert warning in p.stderr
+
+    def test_branch_template_author_app(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, 'branch_template: "{author}/{app}/{number}-{slug}"\n')
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "--dry-run", "new payment flow")
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "--dry-run", "new payment flow")
+        _assert_parity(b, p)
+        assert json.loads(p.stdout)["BRANCH_NAME"] == "test-user/proj/001-new-payment-flow"
+
+    def test_branch_prefix_shorthand(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, "branch_prefix: feat\n")
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "--dry-run", "new payment flow")
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "--dry-run", "new payment flow")
+        _assert_parity(b, p)
+        assert json.loads(p.stdout)["BRANCH_NAME"] == "feat/001-new-payment-flow"
+
+    def test_template_scopes_existing_branch_numbers(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, 'branch_template: "{author}/{number}-{slug}"\n')
+            subprocess.run(["git", "branch", "test-user/008-scoped"], cwd=proj, check=True)
+            subprocess.run(["git", "branch", "other-user/030-unscoped"], cwd=proj, check=True)
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "--dry-run", "next thing")
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "--dry-run", "next thing")
+        _assert_parity(b, p)
+        assert json.loads(p.stdout)["FEATURE_NUM"] == "009"
+
+    @pytest.mark.parametrize(
+        "template",
+        [
+            'branch_template: "feat/{slug}"\n',
+            'branch_template: "{slug}/{number}-x"\n',
+            'branch_template: "{number}/{slug}-x"\n',
+        ],
+    )
+    def test_invalid_template_rejected(self, tmp_path: Path, template: str):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, template)
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "--dry-run", "desc word")
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "--dry-run", "desc word")
+        assert b.returncode == p.returncode == 1
+        assert p.stderr.strip() == b.stderr.strip()
+
+    def test_git_branch_name_override(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        env = {"GIT_BRANCH_NAME": "team/042-exact-name"}
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "desc word", env_extra=env)
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "desc word", env_extra=env)
+        _assert_parity(b, p)
+        assert json.loads(p.stdout) == {"BRANCH_NAME": "team/042-exact-name", "FEATURE_NUM": "042"}
+
+    def test_git_branch_name_override_persist_hint_matches_bash(
+        self, tmp_path: Path
+    ):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        env = {"GIT_BRANCH_NAME": "feature/$value's-\"quoted\""}
+        b = _run_bash(
+            "create-new-feature-branch.sh",
+            bash_proj,
+            "--json",
+            "desc word",
+            env_extra=env,
+        )
+        p = _run_py(
+            "create-new-feature-branch",
+            py_proj,
+            "--json",
+            "desc word",
+            env_extra=env,
+        )
+        _assert_parity(b, p)
+
+    def test_long_branch_name_truncated_to_244_bytes(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        long_name = "-".join(["word"] * 60)
+        b = _run_bash(
+            "create-new-feature-branch.sh", bash_proj,
+            "--json", "--dry-run", "--short-name", long_name, "desc",
+        )
+        p = _run_py(
+            "create-new-feature-branch", py_proj,
+            "--json", "--dry-run", "--short-name", long_name, "desc",
+        )
+        _assert_parity(b, p)
+        assert len(json.loads(p.stdout)["BRANCH_NAME"].encode()) <= 244
+
+    def test_existing_branch_errors_without_flag(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            subprocess.run(["git", "branch", "001-user-auth"], cwd=proj, check=True)
+        args = ("--json", "--number", "1", "--short-name", "user-auth", "desc")
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, *args)
+        p = _run_py("create-new-feature-branch", py_proj, *args)
+        assert b.returncode == p.returncode == 1
+        assert p.stderr.strip() == b.stderr.strip()
+
+    def test_existing_branch_switches_with_allow_flag(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            subprocess.run(["git", "branch", "001-user-auth"], cwd=proj, check=True)
+        args = ("--json", "--number", "1", "--short-name", "user-auth", "--allow-existing-branch", "desc")
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, *args)
+        p = _run_py("create-new-feature-branch", py_proj, *args)
+        _assert_parity(b, p)
+        for proj in (bash_proj, py_proj):
+            branch = subprocess.run(
+                ["git", "rev-parse", "--abbrev-ref", "HEAD"],
+                cwd=proj,
+                capture_output=True,
+                text=True,
+            ).stdout.strip()
+            assert branch == "001-user-auth"
+
+    def test_no_git_graceful_degradation(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path, git=False)
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "offline feature")
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "offline feature")
+        _assert_parity(b, p)
+        assert "skipped branch creation" in p.stderr
+
+    def test_missing_git_executable_gracefully_degrades(
+        self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+    ):
+        module = runpy.run_path(str(EXT_PY / "create_new_feature_branch.py"))
+        monkeypatch.setenv("PATH", "")
+
+        assert module["_git_lines"](tmp_path, "status") == []
+
+    def test_windows_persist_hint_quotes_branch_name(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        module = runpy.run_path(str(EXT_PY / "create_new_feature_branch.py"))
+        monkeypatch.setattr(module["os"], "name", "nt")
+
+        result = module["_persist_hint"](
+            "GIT_BRANCH_NAME", "feature/$value's-\"quoted\""
+        )
+
+        assert (
+            result
+            == "$env:GIT_BRANCH_NAME = 'feature/$value''s-\"quoted\"'"
+        )
+
+    def test_shell_specific_persist_hint_can_be_ignored_for_parity(self):
+        bash_stderr = (
+            "[specify] Warning\n"
+            "# To persist: export SPECIFY_FEATURE=feature/name\n"
+        )
+        windows_stderr = (
+            "[specify] Warning\n"
+            "# To persist: $env:SPECIFY_FEATURE = 'feature/name'\n"
+        )
+
+        assert _without_persist_hint(bash_stderr) == _without_persist_hint(
+            windows_stderr
+        )
+
+    def test_assert_parity_ignores_windows_persist_hint(
+        self, monkeypatch: pytest.MonkeyPatch
+    ):
+        monkeypatch.setattr(os, "name", "nt")
+        bash_result = subprocess.CompletedProcess(
+            args=[], returncode=0, stdout="", stderr=(
+                "[specify] Warning\n"
+                "# To persist: export SPECIFY_FEATURE=feature/name\n"
+            )
+        )
+        py_result = subprocess.CompletedProcess(
+            args=[], returncode=0, stdout="", stderr=(
+                "[specify] Warning\n"
+                "# To persist: $env:SPECIFY_FEATURE = 'feature/name'\n"
+            )
+        )
+
+        _assert_parity(bash_result, py_result)
+
+    def test_empty_description_errors(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        b = _run_bash("create-new-feature-branch.sh", bash_proj, "--json", "   ")
+        p = _run_py("create-new-feature-branch", py_proj, "--json", "   ")
+        assert b.returncode == p.returncode == 1
+        assert p.stderr.strip() == b.stderr.strip()
+        assert "cannot be empty or contain only whitespace" in p.stderr
+
+    def test_specify_init_dir_resolves_target_project(self, tmp_path: Path):
+        # The script is installed under host_proj, so script_file-based
+        # discovery (and cwd-based discovery, since we run from elsewhere)
+        # would resolve host_proj, not target_proj. host_proj has no specs
+        # (next number 001); target_proj already has 007-existing (next
+        # number 008). Only honoring SPECIFY_INIT_DIR produces 008, so this
+        # proves the env var -- not script location or cwd -- controls
+        # resolution.
+        host_proj = _setup_py_project(tmp_path / "host")
+        target_proj = _setup_py_project(tmp_path / "target")
+        (target_proj / "specs" / "007-existing").mkdir(parents=True)
+        elsewhere = tmp_path / "elsewhere"
+        elsewhere.mkdir()
+        p = _run_py(
+            "create-new-feature-branch", host_proj,
+            "--json", "--dry-run", "init dir feature",
+            env_extra={"SPECIFY_INIT_DIR": str(target_proj)},
+            run_cwd=elsewhere,
+        )
+        assert p.returncode == 0
+        assert json.loads(p.stdout)["FEATURE_NUM"] == "008"
+
+    def test_specify_init_dir_without_core_errors(self, tmp_path: Path):
+        _, py_proj = _twin_projects(tmp_path)
+        (
+            py_proj / ".specify" / "scripts" / "python" / "common.py"
+        ).unlink()
+        p = _run_py(
+            "create-new-feature-branch", py_proj,
+            "--json", "desc word",
+            env_extra={"SPECIFY_INIT_DIR": str(py_proj)},
+        )
+        assert p.returncode == 1
+        assert "SPECIFY_INIT_DIR requires updated Spec Kit core scripts" in p.stderr
+
+
+@requires_bash
+class TestInitializeRepoParity:
+    def test_initializes_repo_with_default_message(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path, git=False)
+        b = _run_bash("initialize-repo.sh", bash_proj)
+        p = _run_py("initialize-repo", py_proj)
+        _assert_parity(b, p)
+        assert p.stderr.strip() == b.stderr.strip()
+        for proj in (bash_proj, py_proj):
+            message = subprocess.run(
+                ["git", "log", "-1", "--format=%s"],
+                cwd=proj,
+                capture_output=True,
+                text=True,
+            ).stdout.strip()
+            assert message == "[Spec Kit] Initial commit"
+
+    def test_custom_commit_message(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path, git=False)
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, 'init_commit_message: "Custom initial commit"\n')
+        b = _run_bash("initialize-repo.sh", bash_proj)
+        p = _run_py("initialize-repo", py_proj)
+        _assert_parity(b, p)
+        for proj in (bash_proj, py_proj):
+            message = subprocess.run(
+                ["git", "log", "-1", "--format=%s"],
+                cwd=proj,
+                capture_output=True,
+                text=True,
+            ).stdout.strip()
+            assert message == "Custom initial commit"
+
+    def test_skips_existing_repo(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        b = _run_bash("initialize-repo.sh", bash_proj)
+        p = _run_py("initialize-repo", py_proj)
+        _assert_parity(b, p)
+        assert p.stderr.strip() == b.stderr.strip()
+        assert "already initialized" in p.stderr
+
+
+@requires_bash
+class TestAutoCommitParity:
+    def _dirty(self, proj: Path) -> None:
+        (proj / "change.txt").write_text("dirty\n", encoding="utf-8")
+
+    def _last_message(self, proj: Path) -> str:
+        return subprocess.run(
+            ["git", "log", "-1", "--format=%s"],
+            cwd=proj,
+            capture_output=True,
+            text=True,
+        ).stdout.strip()
+
+    def test_disabled_by_default(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, "auto_commit:\n  after_specify:\n    enabled: false\n")
+            self._dirty(proj)
+        b = _run_bash("auto-commit.sh", bash_proj, "after_specify")
+        p = _run_py("auto-commit", py_proj, "after_specify")
+        _assert_parity(b, p)
+        assert self._last_message(py_proj) == "seed"
+
+    def test_ignores_unterminated_final_config_line(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        config = "auto_commit:\n  after_specify:\n    enabled: true"
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, config)
+            self._dirty(proj)
+        b = _run_bash("auto-commit.sh", bash_proj, "after_specify")
+        p = _run_py("auto-commit", py_proj, "after_specify")
+        _assert_parity(b, p)
+        assert self._last_message(py_proj) == "seed"
+
+    def test_enabled_per_command_with_custom_message(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        config = (
+            "auto_commit:\n"
+            "  default: false\n"
+            "  after_specify:\n"
+            "    enabled: true\n"
+            '    message: "spec done"\n'
+        )
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, config)
+            self._dirty(proj)
+        b = _run_bash("auto-commit.sh", bash_proj, "after_specify")
+        p = _run_py("auto-commit", py_proj, "after_specify")
+        _assert_parity(b, p)
+        assert p.stderr.strip() == b.stderr.strip()
+        assert self._last_message(bash_proj) == self._last_message(py_proj) == "spec done"
+
+    def test_default_true_applies_to_unlisted_event(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, "auto_commit:\n  default: true\n")
+            self._dirty(proj)
+        b = _run_bash("auto-commit.sh", bash_proj, "after_plan")
+        p = _run_py("auto-commit", py_proj, "after_plan")
+        _assert_parity(b, p)
+        expected = "[Spec Kit] Auto-commit after plan"
+        assert self._last_message(bash_proj) == self._last_message(py_proj) == expected
+
+    def test_explicit_false_beats_default_true(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        config = "auto_commit:\n  default: true\n  after_specify:\n    enabled: false\n"
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, config)
+            self._dirty(proj)
+        b = _run_bash("auto-commit.sh", bash_proj, "after_specify")
+        p = _run_py("auto-commit", py_proj, "after_specify")
+        _assert_parity(b, p)
+        assert self._last_message(py_proj) == "seed"
+
+    def test_before_event_message(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, "auto_commit:\n  before_plan:\n    enabled: true\n")
+            self._dirty(proj)
+        b = _run_bash("auto-commit.sh", bash_proj, "before_plan")
+        p = _run_py("auto-commit", py_proj, "before_plan")
+        _assert_parity(b, p)
+        expected = "[Spec Kit] Auto-commit before plan"
+        assert self._last_message(bash_proj) == self._last_message(py_proj) == expected
+
+    def test_no_changes_skips(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            _write_config(proj, "auto_commit:\n  after_specify:\n    enabled: true\n")
+            subprocess.run(["git", "add", "-A"], cwd=proj, check=True)
+            subprocess.run(
+                ["git", "commit", "-q", "-m", "clean"],
+                cwd=proj,
+                check=True,
+                env={**os.environ, **_GIT_ENV},
+            )
+        b = _run_bash("auto-commit.sh", bash_proj, "after_specify")
+        p = _run_py("auto-commit", py_proj, "after_specify")
+        _assert_parity(b, p)
+        assert p.stderr.strip() == b.stderr.strip()
+        assert "No changes to commit" in p.stderr
+
+    def test_no_config_file_skips(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        for proj in (bash_proj, py_proj):
+            self._dirty(proj)
+        b = _run_bash("auto-commit.sh", bash_proj, "after_specify")
+        p = _run_py("auto-commit", py_proj, "after_specify")
+        _assert_parity(b, p)
+        assert self._last_message(py_proj) == "seed"
+
+    @pytest.mark.skipif(os.name != "posix", reason="POSIX file permissions")
+    def test_unreadable_config_skips_auto_commit(self, tmp_path: Path):
+        """An unreadable config behaves like a missing one: no traceback, no commit."""
+        if os.geteuid() == 0:
+            pytest.skip("root bypasses file permissions")
+        proj = _setup_py_project(tmp_path / "proj")
+        config = _write_config(
+            proj, "auto_commit:\n  after_specify:\n    enabled: true\n"
+        )
+        self._dirty(proj)
+        config.chmod(0o000)
+        try:
+            p = _run_py("auto-commit", proj, "after_specify")
+        finally:
+            config.chmod(0o644)
+        assert p.returncode == 0
+        assert "Traceback" not in p.stderr
+        assert self._last_message(proj) == "seed"
+
+    def test_missing_event_argument_errors(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path)
+        b = _run_bash("auto-commit.sh", bash_proj)
+        p = _run_py("auto-commit", py_proj)
+        assert b.returncode == p.returncode == 1
+
+    def test_not_a_repo_skips(self, tmp_path: Path):
+        bash_proj, py_proj = _twin_projects(tmp_path, git=False)
+        b = _run_bash("auto-commit.sh", bash_proj, "after_specify")
+        p = _run_py("auto-commit", py_proj, "after_specify")
+        _assert_parity(b, p)
+        assert "Not a Git repository" in p.stderr
+
+
+class TestGitCommonPython:
+    """Unit tests for git_common.py (imported directly)."""
+
+    @pytest.fixture()
+    def git_common(self):
+        sys.path.insert(0, str(EXT_PY))
+        try:
+            import git_common
+
+            yield git_common
+        finally:
+            sys.path.remove(str(EXT_PY))
+            sys.modules.pop("git_common", None)
+
+    def test_has_git(self, git_common, tmp_path: Path):
+        assert git_common.has_git(tmp_path) is False
+        _init_git(tmp_path)
+        assert git_common.has_git(tmp_path) is True
+
+    @pytest.mark.parametrize(
+        ("branch", "expected"),
+        [
+            ("001-feature-name", True),
+            ("1234-feature-name", True),
+            ("20260319-143022-feature-name", True),
+            ("feat/004-name", True),
+            ("main", False),
+            ("2026031-143022", False),
+            ("20260319-143022", False),
+            ("2026031-143022-slug", False),
+        ],
+    )
+    def test_check_feature_branch(self, git_common, branch: str, expected: bool):
+        assert git_common.check_feature_branch(branch, True) is expected
+
+    def test_check_feature_branch_no_git_warns_but_passes(self, git_common, capsys):
+        assert git_common.check_feature_branch("main", False) is True
+        assert "skipped branch validation" in capsys.readouterr().err

tests/extensions/test_extension_agent_context.py

@@ -25,6 +25,14 @@ BASH = shutil.which("bash")
 POWERSHELL = (
     shutil.which("pwsh") or shutil.which("powershell.exe") or shutil.which("powershell")
 )
+# On Windows, prefer the built-in Windows PowerShell 5.1 (.NET Framework) when a
+# test needs to exercise a 5.1-specific code path; fall back to whatever
+# POWERSHELL resolves to elsewhere.
+WINDOWS_POWERSHELL = (
+    (shutil.which("powershell.exe") or shutil.which("powershell") or POWERSHELL)
+    if os.name == "nt"
+    else POWERSHELL
+)
 
 
 def _write_ext_config(project_root: Path, **overrides: object) -> None:
@@ -279,12 +287,14 @@ def shlex_quote(value: str) -> str:
     return "'" + value.replace("'", "'\"'\"'") + "'"
 
 
-def _run_powershell_agent_context_script(project_root: Path) -> subprocess.CompletedProcess:
+def _run_powershell_agent_context_script(
+    project_root: Path, powershell: str | None = None
+) -> subprocess.CompletedProcess:
     script = EXT_DIR / "scripts" / "powershell" / "update-agent-context.ps1"
     env = _bundled_script_env(project_root)
     return subprocess.run(
         [
-            POWERSHELL,
+            powershell or POWERSHELL,
             "-NoProfile",
             "-ExecutionPolicy",
             "Bypass",
@@ -412,6 +422,29 @@ class TestBundledUpdaterPathValidation:
         assert output.count("agent-context: updated CLAUDE.md") == 1
         assert "agent-context: updated agents.md" not in output
 
+    @requires_bash
+    def test_bash_script_discovers_nested_plan(self, tmp_path):
+        """Plan discovery recurses into scoped layouts (#3024)."""
+        project = tmp_path / "project"
+        project.mkdir()
+        _install_agent_context_config(
+            project,
+            context_file="AGENTS.md",
+            context_files=[],
+        )
+        plan = project / "specs" / "scope" / "001-feature" / "plan.md"
+        plan.parent.mkdir(parents=True)
+        plan.write_text("# Plan\n", encoding="utf-8")
+
+        result = _run_bash_agent_context_script(project)
+
+        assert result.returncode == 0, result.stderr + result.stdout
+        text = (project / "AGENTS.md").read_text(encoding="utf-8")
+        # The old one-level glob (specs/*/plan.md) would find nothing here, so no
+        # "at" line would be emitted. Normalize separators before matching: on
+        # MSYS bash the emitted path may be absolute with backslashes.
+        assert "specs/scope/001-feature/plan.md" in text.replace("\\", "/")
+
     @requires_bash
     def test_bash_script_falls_back_from_invalid_speckit_python(self, tmp_path):
         project = tmp_path / "project"
@@ -484,6 +517,33 @@ class TestBundledUpdaterPathValidation:
         assert output.count("agent-context: updated CLAUDE.md") == 1
         assert "agent-context: updated agents.md" not in output
 
+    @pytest.mark.skipif(WINDOWS_POWERSHELL is None, reason="PowerShell not available")
+    def test_powershell_script_discovers_nested_plan(self, tmp_path):
+        """Plan discovery recurses into scoped layouts (#3024).
+
+        The relative-path fix this covers is specific to Windows PowerShell 5.1
+        (.NET Framework), so prefer ``powershell.exe`` over ``pwsh`` here to
+        actually exercise that failure mode on Windows.
+        """
+        project = tmp_path / "project"
+        project.mkdir()
+        _install_agent_context_config(
+            project,
+            context_file="AGENTS.md",
+            context_files=[],
+        )
+        plan = project / "specs" / "scope" / "001-feature" / "plan.md"
+        plan.parent.mkdir(parents=True)
+        plan.write_text("# Plan\n", encoding="utf-8")
+
+        result = _run_powershell_agent_context_script(
+            project, powershell=WINDOWS_POWERSHELL
+        )
+
+        assert result.returncode == 0, result.stderr + result.stdout
+        text = (project / "AGENTS.md").read_text(encoding="utf-8")
+        assert "at specs/scope/001-feature/plan.md" in text
+
     @pytest.mark.skipif(POWERSHELL is None, reason="PowerShell not available")
     def test_powershell_script_falls_back_from_invalid_speckit_python(self, tmp_path):
         project = tmp_path / "project"

tests/hooks/.specify/extensions.yml

@@ -6,7 +6,7 @@ hooks:
       extension: "test-extension"
       command: "pre_implement_test"
       description: "Test before implement hook execution"
-      
+
   after_implement:
     - id: post_test
       enabled: true

tests/hooks/TESTING.md

@@ -7,7 +7,7 @@ This directory contains a mock project to verify that LLM agents correctly ident
 1. Open a chat with an LLM (like GitHub Copilot) in this project.
 2. Ask it to generate tasks for the current directory:
    > "Please follow `/speckit.tasks` for the `./tests/hooks` directory."
-3. **Expected Behavior**: 
+3. **Expected Behavior**:
    - Before doing any generation, the LLM should notice the `AUTOMATIC Pre-Hook` in `.specify/extensions.yml` under `before_tasks`.
    - It should state it is executing `EXECUTE_COMMAND: pre_tasks_test`.
    - It should then proceed to read the `.md` docs and produce a `tasks.md`.

tests/integration/test_bundler_install_flow.py

@@ -11,7 +11,7 @@ import pytest
 
 from specify_cli.bundler import BundlerError
 from specify_cli.bundler.models.manifest import BundleManifest
-from specify_cli.bundler.models.records import load_records
+from specify_cli.bundler.models.records import load_records, records_path
 from specify_cli.bundler.services.installer import install_bundle, remove_bundle
 from specify_cli.bundler.services.resolver import resolve_install_plan
 from tests.bundler_helpers import FakeInstaller, make_project, valid_manifest_dict
@@ -97,6 +97,212 @@ def test_remove_unknown_bundle_errors(tmp_path: Path):
         remove_bundle(tmp_path, "ghost", FakeInstaller())
 
 
+def test_remove_converts_raw_installer_exception_to_bundler_error(tmp_path: Path):
+    """A raw exception from a primitive installer (e.g. an OSError from an
+    unreadable workflow registry surfacing through _WorkflowKindManager's
+    fail-closed construction) must not propagate uncaught out of
+    remove_bundle: install_bundle already converts any non-BundlerError
+    exception into a clean BundlerError, but remove_bundle had no such
+    conversion, so the CLI's `bundle remove` (which only catches
+    BundlerError) would let a raw exception through with no clean message
+    and no removal side effects should occur either."""
+    make_project(tmp_path)
+    manifest = BundleManifest.from_dict(valid_manifest_dict())
+    installer = FakeInstaller()
+    install_bundle(tmp_path, _plan(manifest), installer, manifest=manifest)
+
+    def boom(project_root, component):
+        raise OSError("workflow registry unreadable")
+
+    with pytest.MonkeyPatch.context() as mp:
+        mp.setattr(installer, "is_installed", boom)
+        with pytest.raises(BundlerError):
+            remove_bundle(tmp_path, "demo-bundle", installer)
+
+    # No removal side effects: the bundle record must still be present.
+    assert {r.bundle_id for r in load_records(tmp_path)} == {"demo-bundle"}
+
+
+def test_remove_partial_failure_message_reflects_partial_state(tmp_path: Path):
+    """A failure can occur after earlier components in the same bundle have
+    already been removed from disk. The bundle record is left unchanged
+    (save_records never runs on this path), so it still claims the bundle
+    fully installed -- but the message must not claim "No changes were
+    recorded" when components were, in fact, already removed."""
+    make_project(tmp_path)
+    manifest = BundleManifest.from_dict(valid_manifest_dict())
+    installer = FakeInstaller()
+    install_bundle(tmp_path, _plan(manifest), installer, manifest=manifest)
+
+    real_remove = installer.remove
+    calls = {"n": 0}
+
+    def remove_then_fail(project_root, component):
+        calls["n"] += 1
+        if calls["n"] == 1:
+            return real_remove(project_root, component)
+        raise OSError("disk full")
+
+    with pytest.MonkeyPatch.context() as mp:
+        mp.setattr(installer, "remove", remove_then_fail)
+        with pytest.raises(BundlerError) as exc_info:
+            remove_bundle(tmp_path, "demo-bundle", installer)
+
+    message = str(exc_info.value)
+    assert "no changes were recorded" not in message.lower()
+    assert {r.bundle_id for r in load_records(tmp_path)} == {"demo-bundle"}
+
+
+def test_remove_bundler_error_from_installer_after_partial_removal_reports_partial_state(
+    tmp_path: Path,
+):
+    """If the primitive installer itself raises BundlerError (not a raw/
+    unexpected exception) after an earlier component in the same bundle was
+    already removed, the surfaced message must still carry the same
+    partial-removal detail as the generic-exception path -- a bare
+    ``except BundlerError: raise`` would re-raise the installer's original
+    message verbatim with no mention that the project may now be partially
+    uninstalled."""
+    make_project(tmp_path)
+    manifest = BundleManifest.from_dict(valid_manifest_dict())
+    installer = FakeInstaller()
+    install_bundle(tmp_path, _plan(manifest), installer, manifest=manifest)
+
+    real_remove = installer.remove
+    calls = {"n": 0}
+
+    def remove_then_raise_bundler_error(project_root, component):
+        calls["n"] += 1
+        if calls["n"] == 1:
+            return real_remove(project_root, component)
+        raise BundlerError("kind manager refused removal")
+
+    with pytest.MonkeyPatch.context() as mp:
+        mp.setattr(installer, "remove", remove_then_raise_bundler_error)
+        with pytest.raises(BundlerError) as exc_info:
+            remove_bundle(tmp_path, "demo-bundle", installer)
+
+    message = str(exc_info.value)
+    assert "no changes were recorded" not in message.lower()
+    assert "kind manager refused removal" in message
+    assert "partially uninstalled" in message.lower()
+    assert {r.bundle_id for r in load_records(tmp_path)} == {"demo-bundle"}
+
+
+def test_remove_bundler_error_from_installer_with_zero_removed_reports_no_changes(
+    tmp_path: Path,
+):
+    """When the installer raises BundlerError before anything was actually
+    removed, the message should not misleadingly claim partial state."""
+    make_project(tmp_path)
+    manifest = BundleManifest.from_dict(valid_manifest_dict())
+    installer = FakeInstaller()
+    install_bundle(tmp_path, _plan(manifest), installer, manifest=manifest)
+
+    def boom(project_root, component):
+        raise BundlerError("kind manager unavailable")
+
+    with pytest.MonkeyPatch.context() as mp:
+        mp.setattr(installer, "is_installed", boom)
+        with pytest.raises(BundlerError) as exc_info:
+            remove_bundle(tmp_path, "demo-bundle", installer)
+
+    message = str(exc_info.value)
+    assert "no components were removed" in message.lower()
+    assert "no removal was attempted" in message.lower()
+    assert "partially uninstalled" not in message.lower()
+    assert "kind manager unavailable" in message
+    assert {r.bundle_id for r in load_records(tmp_path)} == {"demo-bundle"}
+
+
+def test_remove_zero_completed_removals_still_cautions_about_partial_changes(
+    tmp_path: Path,
+):
+    """`result.uninstalled` only records a component after its `remove()`
+    call returns successfully. If the very first `remove()` call itself
+    raises after already deleting some files, zero completed removals are
+    recorded even though the project may already be partially uninstalled --
+    the zero-count message must not claim "No components were removed" as
+    an unqualified fact; it must caution that the failing component may
+    have made partial changes before raising."""
+    make_project(tmp_path)
+    manifest = BundleManifest.from_dict(valid_manifest_dict())
+    installer = FakeInstaller()
+    install_bundle(tmp_path, _plan(manifest), installer, manifest=manifest)
+
+    def boom(project_root, component):
+        # Simulates a remove() that deletes some files before raising --
+        # from the caller's perspective this component was never recorded
+        # as completed, but disk state may already be partially changed.
+        raise OSError("disk full partway through removal")
+
+    with pytest.MonkeyPatch.context() as mp:
+        mp.setattr(installer, "remove", boom)
+        with pytest.raises(BundlerError) as exc_info:
+            remove_bundle(tmp_path, "demo-bundle", installer)
+
+    message = str(exc_info.value)
+    assert "no components were removed" in message.lower()
+    assert "partial" in message.lower()
+    assert "partially uninstalled" in message.lower()
+    assert {r.bundle_id for r in load_records(tmp_path)} == {"demo-bundle"}
+
+
+def test_remove_record_save_failure_reports_partial_state(tmp_path: Path):
+    make_project(tmp_path)
+    manifest = BundleManifest.from_dict(valid_manifest_dict())
+    installer = FakeInstaller()
+    install_bundle(tmp_path, _plan(manifest), installer, manifest=manifest)
+    record_file = records_path(tmp_path)
+    original_record = record_file.read_bytes()
+
+    def fail_dump(_data, handle, *_args, **_kwargs):
+        handle.write('{"partial":')
+        handle.flush()
+        raise OSError("disk full")
+
+    with pytest.MonkeyPatch.context() as mp:
+        mp.setattr(
+            "specify_cli.bundler.lib.yamlio.json.dump",
+            fail_dump,
+        )
+        with pytest.raises(BundlerError) as exc_info:
+            remove_bundle(tmp_path, "demo-bundle", installer)
+
+    message = str(exc_info.value)
+    assert "disk full" in message
+    assert "partially uninstalled" in message.lower()
+    assert installer.installed == set()
+    assert record_file.read_bytes() == original_record
+    assert {r.bundle_id for r in load_records(tmp_path)} == {"demo-bundle"}
+
+
+def test_remove_record_save_failure_without_remove_attempt_is_not_partial(
+    tmp_path: Path,
+):
+    make_project(tmp_path)
+    manifest = BundleManifest.from_dict(valid_manifest_dict())
+    installer = FakeInstaller()
+    install_bundle(tmp_path, _plan(manifest), installer, manifest=manifest)
+    installer.installed.clear()
+
+    def fail_save(*_args, **_kwargs):
+        raise OSError("disk full")
+
+    with pytest.MonkeyPatch.context() as mp:
+        mp.setattr(
+            "specify_cli.bundler.services.installer.save_records",
+            fail_save,
+        )
+        with pytest.raises(BundlerError) as exc_info:
+            remove_bundle(tmp_path, "demo-bundle", installer)
+
+    message = str(exc_info.value)
+    assert "no removal was attempted" in message.lower()
+    assert "partially uninstalled" not in message.lower()
+    assert {r.bundle_id for r in load_records(tmp_path)} == {"demo-bundle"}
+
+
 def test_remove_reports_uninstalled_not_installed(tmp_path: Path):
     make_project(tmp_path)
     manifest = BundleManifest.from_dict(valid_manifest_dict())
@@ -128,7 +334,7 @@ def test_remove_counts_only_components_actually_removed(tmp_path: Path):
 
     assert len(result.uninstalled) == 3
     assert (gone.kind, gone.id) not in installer.remove_calls
-    assert gone in result.skipped
+    assert gone not in result.skipped
     make_project(tmp_path)
     manifest = BundleManifest.from_dict(valid_manifest_dict())
     installer = FakeInstaller()

tests/integration/test_bundler_local_install.py

@@ -112,3 +112,62 @@ def test_install_bundled_extension_from_zip_offline(tmp_path: Path):
         assert not ExtensionManager(project).registry.is_installed("agent-context")
     finally:
         os.chdir(previous)
+
+
+def test_download_manifest_rejects_file_url(tmp_path: Path):
+    """A catalog ``file://`` download_url is rejected — catalog URLs are
+    HTTPS-only, matching extensions/presets/workflows. Disk installs go through
+    the positional path (see the local-source tests above), not download_url.
+    """
+    from types import SimpleNamespace
+
+    from specify_cli.commands.bundle import _download_manifest
+
+    manifest_path = write_manifest(tmp_path / "my bundles")
+    resolved = SimpleNamespace(
+        entry=SimpleNamespace(id="demo-bundle", download_url=manifest_path.as_uri())
+    )
+
+    with pytest.raises(BundlerError, match="bundle install"):
+        _download_manifest(resolved, offline=True)
+
+
+def test_download_manifest_rejects_bare_path(tmp_path: Path):
+    """A bare filesystem path download_url is likewise rejected."""
+    from types import SimpleNamespace
+
+    from specify_cli.commands.bundle import _download_manifest
+
+    manifest_path = write_manifest(tmp_path / "plain")
+    resolved = SimpleNamespace(
+        entry=SimpleNamespace(id="demo-bundle", download_url=str(manifest_path))
+    )
+
+    with pytest.raises(BundlerError, match="bundle install"):
+        _download_manifest(resolved, offline=True)
+
+
+def test_local_install_still_resolves_via_positional_path(tmp_path: Path):
+    """The supported local route — a positional path, not a download_url —
+    still resolves the manifest via _local_manifest_source."""
+    manifest_path = write_manifest(tmp_path / "my bundles")
+    manifest = _local_manifest_source(str(manifest_path))
+    assert manifest is not None
+    assert manifest.bundle.id == "demo-bundle"
+
+
+def test_download_manifest_rejects_non_https_url_even_offline(tmp_path: Path):
+    """A non-HTTPS download_url must report the HTTPS problem, not a misleading
+    'Network access disabled', even under --offline (scheme is validated before
+    the offline gate)."""
+    from types import SimpleNamespace
+
+    from specify_cli.commands.bundle import _download_manifest
+
+    resolved = SimpleNamespace(
+        entry=SimpleNamespace(
+            id="demo-bundle", download_url="http://example.com/bundle.zip"
+        )
+    )
+    with pytest.raises(BundlerError, match="HTTPS"):
+        _download_manifest(resolved, offline=True)

tests/integrations/test_cli.py

@@ -115,6 +115,63 @@ class TestInitIntegrationFlag:
         data = json.loads((project / ".specify" / "integration.json").read_text(encoding="utf-8"))
         assert data["integration"] == specify_cli.DEFAULT_INIT_INTEGRATION
 
+    def test_init_here_nonempty_noninteractive_errors_with_force_guidance(self, tmp_path):
+        """`init --here` on a non-empty directory with no confirmation input (empty
+        stdin) must fail fast with guidance to use --force, instead of the bare
+        'Aborted.' from an EOF on typer.confirm. CliRunner with no `input=` provides
+        empty stdin, so typer.confirm raises Abort, which the command converts to the
+        actionable error."""
+        from typer.testing import CliRunner
+        from specify_cli import app
+
+        project = tmp_path / "nonempty-here"
+        project.mkdir()
+        (project / "existing.txt").write_text("keep me", encoding="utf-8")
+        old_cwd = os.getcwd()
+        try:
+            os.chdir(project)
+            result = CliRunner().invoke(app, [
+                "init", "--here", "--integration", "copilot", "--script", "sh", "--ignore-agent-tools",
+            ], catch_exceptions=False)
+        finally:
+            os.chdir(old_cwd)
+
+        assert result.exit_code == 1, result.output
+        assert "--force" in result.output
+        # Aborted before scaffolding: the pre-existing file is untouched.
+        assert (project / "existing.txt").read_text(encoding="utf-8") == "keep me"
+
+    def test_init_here_interactive_cancel_exits_zero(self, tmp_path, monkeypatch):
+        """An interactive Ctrl+C at the merge confirmation (typer.Abort on a TTY)
+        is a normal cancellation — exit 0, "cancelled" — NOT the missing-input
+        --force error, which is reserved for non-interactive EOF. Guards the
+        regression where Abort was caught unconditionally and every cancel became
+        an exit-1 --force error."""
+        from typer.testing import CliRunner
+        from specify_cli import app
+        import specify_cli.commands.init as init_mod
+
+        # Simulate an interactive terminal so the Abort is treated as a cancel.
+        monkeypatch.setattr(init_mod, "_stdin_is_interactive", lambda: True)
+
+        project = tmp_path / "cancel-here"
+        project.mkdir()
+        (project / "existing.txt").write_text("keep me", encoding="utf-8")
+        old_cwd = os.getcwd()
+        try:
+            os.chdir(project)
+            # No input → typer.confirm raises Abort (stands in for Ctrl+C).
+            result = CliRunner().invoke(app, [
+                "init", "--here", "--integration", "copilot", "--script", "sh", "--ignore-agent-tools",
+            ], catch_exceptions=False)
+        finally:
+            os.chdir(old_cwd)
+
+        assert result.exit_code == 0, result.output
+        assert "cancelled" in result.output.lower()
+        assert "--force" not in result.output  # not the missing-input error
+        assert (project / "existing.txt").read_text(encoding="utf-8") == "keep me"
+
     def test_integration_copilot_auto_promotes(self, tmp_path):
         from typer.testing import CliRunner
         from specify_cli import app
@@ -257,6 +314,18 @@ class TestInitIntegrationFlag:
         assert (scripts_dir / "setup-plan.sh").exists()
         assert (templates_dir / "plan-template.md").exists()
 
+    def test_shared_infra_installs_python_scripts_for_py(self, tmp_path):
+        from specify_cli import _install_shared_infra
+
+        project = tmp_path / "python-scripts"
+        project.mkdir()
+
+        _install_shared_infra(project, "py")
+
+        assert (
+            project / ".specify" / "scripts" / "python" / "common.py"
+        ).exists()
+
     def test_shared_infra_removes_stale_managed_script(self, tmp_path):
         """A managed script the core no longer ships (e.g. the legacy
         update-agent-context.sh, superseded by the agent-context extension) is
@@ -835,7 +904,8 @@ class TestInitIntegrationFlag:
         assert (scripts_dir / "common.sh").read_text(encoding="utf-8") != custom_content
 
     def test_init_here_without_force_preserves_shared_infra(self, tmp_path):
-        """E2E: specify init --here (no --force) preserves existing shared infra files."""
+        """E2E: confirming the merge with piped "y" (no --force) preserves
+        existing shared infra files (unlike --force, which overwrites them)."""
         from typer.testing import CliRunner
         from specify_cli import app
 

tests/integrations/test_integration_base_markdown.py

@@ -253,6 +253,7 @@ class MarkdownIntegrationTests:
                      "spec-template.md", "tasks-template.md"]:
             files.append(f".specify/templates/{name}")
 
+        files.append(".specify/memory/.constitution-template.json")
         files.append(".specify/memory/constitution.md")
         # Bundled workflow
         files.append(".specify/workflows/speckit/workflow.yml")

tests/integrations/test_integration_base_skills.py

@@ -399,6 +399,7 @@ class SkillsIntegrationTests:
             ".specify/integration.json",
             f".specify/integrations/{self.KEY}.manifest.json",
             ".specify/integrations/speckit.manifest.json",
+            ".specify/memory/.constitution-template.json",
             ".specify/memory/constitution.md",
         ]
         # Script variant

tests/integrations/test_integration_base_toml.py

@@ -517,6 +517,7 @@ class TomlIntegrationTests:
         ]:
             files.append(f".specify/templates/{name}")
 
+        files.append(".specify/memory/.constitution-template.json")
         files.append(".specify/memory/constitution.md")
         # Bundled workflow
         files.append(".specify/workflows/speckit/workflow.yml")

tests/integrations/test_integration_base_yaml.py

@@ -201,6 +201,36 @@ class YamlIntegrationTests:
         parsed = yaml.safe_load("\n".join(yaml_lines))
         assert parsed["prompt"].rstrip("\n") == body
 
+    def test_yaml_prompt_with_control_characters_stays_valid(self):
+        """A body containing control characters must still produce parseable YAML.
+
+        YAML forbids C0 control characters (except tab and newline), DEL,
+        C1 controls, lone surrogates and U+FFFE/U+FFFF in every scalar form,
+        and YAML 1.1 treats NEL (U+0085), LS (U+2028) and PS (U+2029) as
+        line breaks that corrupt a literal block scalar's structure. The
+        renderer falls back to an escaped double-quoted scalar for such
+        bodies."""
+        for ch in (
+            "\x08", "\x0c", "\x1b", "\x7f",
+            "\x80", "\x84", "\x85", "\x86", "\x9f",
+            "\u2028", "\u2029",
+            "\ud800", "\udfff", "\ufffe", "\uffff",
+        ):
+            body = f"before{ch}after\nsecond line"
+            rendered = YamlIntegration._render_yaml("Title", "Desc", body, "src")
+            parsed = yaml.safe_load(rendered)
+            assert parsed["prompt"].rstrip("\n") == body, f"char {ch!r} round-trip"
+
+    def test_yaml_prompt_with_bare_carriage_return_stays_valid(self):
+        """A bare CR (not part of CRLF) must not break the generated YAML.
+
+        Inside a block scalar a lone \r acts as a line break, corrupting
+        the document structure."""
+        body = "line1\rstill line1\nline2"
+        rendered = YamlIntegration._render_yaml("Title", "Desc", body, "src")
+        parsed = yaml.safe_load(rendered)
+        assert parsed["prompt"].rstrip("\n") == body
+
     def test_plan_command_has_no_context_placeholder(self, tmp_path):
         """The generated plan command must not carry a context-file placeholder.
 
@@ -401,6 +431,7 @@ class YamlIntegrationTests:
         ]:
             files.append(f".specify/templates/{name}")
 
+        files.append(".specify/memory/.constitution-template.json")
         files.append(".specify/memory/constitution.md")
         # Bundled workflow
         files.append(".specify/workflows/speckit/workflow.yml")

tests/integrations/test_integration_catalog.py

@@ -84,6 +84,20 @@ class TestCatalogURLValidation:
         with pytest.raises(IntegrationCatalogError, match="valid URL"):
             IntegrationCatalog._validate_catalog_url(url)
 
+    @pytest.mark.parametrize(
+        "url",
+        [
+            "https://[::1",                 # unclosed ipv6 bracket
+            "https://[not-an-ip]/c.json",   # bracketed non-ip host
+        ],
+    )
+    def test_malformed_url_rejected_cleanly(self, url):
+        # A malformed authority makes urlparse/hostname raise ValueError. The
+        # validator must turn that into its normal catalog error, not leak a
+        # raw ValueError to the caller.
+        with pytest.raises(IntegrationCatalogError, match="malformed"):
+            IntegrationCatalog._validate_catalog_url(url)
+
 
 # ---------------------------------------------------------------------------
 # IntegrationCatalog — active catalogs

tests/integrations/test_integration_cline.py

@@ -214,6 +214,7 @@ class TestClineIntegration(MarkdownIntegrationTests):
         ]:
             files.append(f".specify/templates/{name}")
 
+        files.append(".specify/memory/.constitution-template.json")
         files.append(".specify/memory/constitution.md")
         # Bundled workflow
         files.append(".specify/workflows/speckit/workflow.yml")

tests/integrations/test_integration_copilot.py

@@ -252,6 +252,7 @@ class TestCopilotIntegration:
             ".specify/templates/plan-template.md",
             ".specify/templates/spec-template.md",
             ".specify/templates/tasks-template.md",
+            ".specify/memory/.constitution-template.json",
             ".specify/memory/constitution.md",
             ".specify/workflows/speckit/workflow.yml",
             ".specify/workflows/workflow-registry.json",
@@ -313,6 +314,7 @@ class TestCopilotIntegration:
             ".specify/templates/plan-template.md",
             ".specify/templates/spec-template.md",
             ".specify/templates/tasks-template.md",
+            ".specify/memory/.constitution-template.json",
             ".specify/memory/constitution.md",
             ".specify/workflows/speckit/workflow.yml",
             ".specify/workflows/workflow-registry.json",
@@ -724,6 +726,7 @@ class TestCopilotSkillsMode:
             ".specify/templates/plan-template.md",
             ".specify/templates/spec-template.md",
             ".specify/templates/tasks-template.md",
+            ".specify/memory/.constitution-template.json",
             ".specify/memory/constitution.md",
             # Bundled workflow
             ".specify/workflows/speckit/workflow.yml",