chore: bump version to 0.12.18

Bumps [actions/setup-dotnet](https://github.com/actions/setup-dotnet) from 5.4.0 to 6.0.0.
- [Release notes](https://github.com/actions/setup-dotnet/releases)
- [Commits](26b0ec14cb...a98b56852c)

---
updated-dependencies:
- dependency-name: actions/setup-dotnet
  dependency-version: 6.0.0
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/ISSUE_TEMPLATE/agent_request.yml

@@ -8,7 +8,7 @@ body:
       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
+        **Currently supported agents**: Amp, Antigravity, Auggie CLI, Claude Code, Cline, CodeBuddy, Codex CLI, Cursor, Devin for Terminal, Firebender, Forge, Gemini CLI, GitHub Copilot, Goose, Grok Build, 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
     id: agent-name

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -76,6 +76,7 @@ body:
         - Gemini CLI
         - GitHub Copilot
         - Goose
+        - Grok Build
         - Hermes Agent
         - IBM Bob
         - Junie

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -70,6 +70,7 @@ body:
         - Gemini CLI
         - GitHub Copilot
         - Goose
+        - Grok Build
         - Hermes Agent
         - IBM Bob
         - Junie

.github/workflows/add-community-extension.lock.yml

@@ -36,7 +36,7 @@
 #   - actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
 #   - actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
 #   - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
-#   - actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+#   - actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
 #   - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
 #   - github/gh-aw-actions/setup@c0338fef4749d08c21f8f975fb0e37efa17dda47 # v0.79.8
 #
@@ -1399,7 +1399,7 @@ jobs:
           mkdir -p /tmp/gh-aw/threat-detection
           touch /tmp/gh-aw/threat-detection/detection.log
       - name: Setup Node.js
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
         with:
           node-version: '24'
           package-manager-cache: false

.github/workflows/add-community-preset.lock.yml

@@ -36,7 +36,7 @@
 #   - actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
 #   - actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
 #   - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
-#   - actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+#   - actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
 #   - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
 #   - github/gh-aw-actions/setup@c0338fef4749d08c21f8f975fb0e37efa17dda47 # v0.79.8
 #
@@ -1399,7 +1399,7 @@ jobs:
           mkdir -p /tmp/gh-aw/threat-detection
           touch /tmp/gh-aw/threat-detection/detection.log
       - name: Setup Node.js
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
         with:
           node-version: '24'
           package-manager-cache: false

.github/workflows/bug-assess.lock.yml

@@ -35,7 +35,7 @@
 #   - actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
 #   - actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
 #   - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
-#   - actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+#   - actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
 #   - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
 #   - github/gh-aw-actions/setup@c0338fef4749d08c21f8f975fb0e37efa17dda47 # v0.79.8
 #
@@ -1344,7 +1344,7 @@ jobs:
           mkdir -p /tmp/gh-aw/threat-detection
           touch /tmp/gh-aw/threat-detection/detection.log
       - name: Setup Node.js
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
         with:
           node-version: '24'
           package-manager-cache: false

.github/workflows/bug-fix.lock.yml

@@ -36,7 +36,7 @@
 #   - actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
 #   - actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
 #   - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
-#   - actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+#   - actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
 #   - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
 #   - github/gh-aw-actions/setup@c0338fef4749d08c21f8f975fb0e37efa17dda47 # v0.79.8
 #
@@ -1405,7 +1405,7 @@ jobs:
           mkdir -p /tmp/gh-aw/threat-detection
           touch /tmp/gh-aw/threat-detection/detection.log
       - name: Setup Node.js
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
         with:
           node-version: '24'
           package-manager-cache: false

.github/workflows/bug-test.lock.yml

@@ -35,7 +35,7 @@
 #   - actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
 #   - actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
 #   - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
-#   - actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+#   - actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
 #   - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
 #   - github/gh-aw-actions/setup@c0338fef4749d08c21f8f975fb0e37efa17dda47 # v0.79.8
 #
@@ -1366,7 +1366,7 @@ jobs:
           mkdir -p /tmp/gh-aw/threat-detection
           touch /tmp/gh-aw/threat-detection/detection.log
       - name: Setup Node.js
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
         with:
           node-version: '24'
           package-manager-cache: false

.github/workflows/docs.yml

@@ -35,7 +35,7 @@ jobs:
           fetch-depth: 0 # Fetch all history for git info
 
       - name: Setup .NET
-        uses: actions/setup-dotnet@26b0ec14cb23fa6904739307f278c14f94c95bf1 # v5.4.0
+        uses: actions/setup-dotnet@a98b56852c35b8e3190ac28c8c2271da59106c68 # v6.0.0
         with:
           dotnet-version: '8.x'
 

.github/workflows/stale.yml

@@ -14,7 +14,7 @@ jobs:
   stale:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@eb5cf3af3ac0a1aa4c9c45633dd1ae542a27a899 # v10
+      - uses: actions/stale@1e223db275d687790206a7acac4d1a11bd6fe629 # v10
         with:
           # Days of inactivity before an issue or PR becomes stale
           days-before-stale: 150

.gitignore

@@ -53,9 +53,10 @@ docs/dev
 
 # The following directories/file are intentionally ignored so that they are not accidentally
 # committed to the repository. They contain the scaffolding `specify init --integration copilot`
-# does and they are meant for dogfooding Spec Kit during its own feature development.
+# (or other agents) does and they are meant for dogfooding Spec Kit during its own feature development.
 .github/agents/
 .github/prompts/
 .github/copilot-instructions.md
+.grok/
 .specify/
 specs/

CHANGELOG.md

@@ -2,6 +2,66 @@
 
 <!-- insert new changelog below this comment -->
 
+## [0.12.18] - 2026-07-17
+
+### Changed
+
+- chore(deps): bump actions/setup-dotnet from 5.4.0 to 6.0.0 (#3574)
+- chore(deps): bump actions/stale from 10.3.0 to 10.4.0 (#3572)
+- chore(deps): bump actions/setup-node from 6.4.0 to 7.0.0 (#3570)
+- docs: weave harness/SDLC framing into landing page (#3567)
+- docs: reframe SDD positioning, modernize install, and de-duplicate walkthroughs (#3565)
+- docs: document extensions.yml hook configuration (#3563)
+- docs: refresh landing page ecosystem stats (#3561)
+- [extension] Add Dotdog extension to community catalog (#3558)
+- Update DocGuard — CDD Enforcement to v0.33.0 (#3559)
+- chore: release 0.12.17, begin 0.12.18.dev0 development (#3560)
+
+## [0.12.17] - 2026-07-16
+
+### Changed
+
+- fix(extensions): resolve __SPECKIT_COMMAND tokens in auto-registered skills (#3544)
+- fix(workflows): fail if/switch steps on non-list branch instead of crashing (#3515)
+- feat(integrations): add Grok Build skills-based integration (#3535)
+- fix(extensions/git): reject negative -Number in create-new-feature-branch.ps1 (#3538)
+- test: cover preset constitution seeding through init CLI (#3297)
+- fix(integration): preserve ai_skills on `use` for skills-mode Copilot (#3550) (#3551)
+- [extension] Add Figma Starter extension to community catalog (#3547)
+- [extension] Add Spec-Kit BDD extension to community catalog (#3548)
+- [extension] Update Quality Gates (Enforcement Layer) extension to v0.3.2 (#3542)
+- chore: release 0.12.16, begin 0.12.17.dev0 development (#3549)
+
+## [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

README.md

@@ -32,7 +32,6 @@
 - [🎯 Experimental Goals](#-experimental-goals)
 - [🔧 Prerequisites](#-prerequisites)
 - [📖 Learn More](#-learn-more)
-- [📋 Detailed Process](#-detailed-process)
 - [💬 Support](#-support)
 - [🙏 Acknowledgements](#-acknowledgements)
 - [📄 License](#-license)
@@ -51,6 +50,12 @@ Requires **[uv](https://docs.astral.sh/uv/)** ([install uv](./docs/install/uv.md
 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
@@ -355,294 +360,7 @@ If you encounter issues with an agent, please open an issue so we can refine the
 ## 📖 Learn More
 
 - **[Complete Spec-Driven Development Methodology](./spec-driven.md)** - Deep dive into the full process
-- **[Detailed Walkthrough](#-detailed-process)** - Step-by-step implementation guide
-
----
-
-## 📋 Detailed Process
-
-<details>
-<summary>Click to expand the detailed step-by-step walkthrough</summary>
-
-You can use the Specify CLI to bootstrap your project, which will bring in the required artifacts in your environment. Run:
-
-```bash
-specify init <project_name>
-```
-
-Or initialize in the current directory:
-
-```bash
-specify init .
-# or use the --here flag
-specify init --here
-# Skip confirmation when the directory already has files
-specify init . --force
-# or
-specify init --here --force
-```
-
-![Specify CLI bootstrapping a new project in the terminal](./media/specify_cli.gif)
-
-In an interactive terminal, you will be prompted to select the coding agent integration you are using. In non-interactive sessions, such as CI or piped runs, `specify init` defaults to GitHub Copilot unless you pass `--integration`. You can also proactively specify the integration directly in the terminal:
-
-```bash
-specify init <project_name> --integration copilot
-specify init <project_name> --integration gemini
-specify init <project_name> --integration codex
-
-# Or in current directory:
-specify init . --integration copilot
-specify init . --integration codex --integration-options="--skills"
-
-# or use --here flag
-specify init --here --integration copilot
-specify init --here --integration codex --integration-options="--skills"
-
-# Force merge into a non-empty current directory
-specify init . --force --integration copilot
-
-# or
-specify init --here --force --integration copilot
-```
-
-The CLI checks that the selected integration's required CLI tool is installed on your machine when that integration has `requires_cli: True`. If you do not have the required tool installed, or you prefer to get the templates without checking for the right tools, use `--ignore-agent-tools` with your command:
-
-```bash
-specify init <project_name> --integration copilot --ignore-agent-tools
-```
-
-### **STEP 1:** Establish project principles
-
-Go to the project folder and run your coding agent. In our example, we're using `claude`.
-
-![Bootstrapping Claude Code environment](./media/bootstrap-claude-code.gif)
-
-You will know that things are configured correctly if you see the `/speckit.constitution`, `/speckit.specify`, `/speckit.plan`, `/speckit.tasks`, and `/speckit.implement` commands available.
-
-The first step should be establishing your project's governing principles using the `/speckit.constitution` command. This helps ensure consistent decision-making throughout all subsequent development phases:
-
-```text
-/speckit.constitution Create principles focused on code quality, testing standards, user experience consistency, and performance requirements. Include governance for how these principles should guide technical decisions and implementation choices.
-```
-
-This step creates or updates the `.specify/memory/constitution.md` file with your project's foundational guidelines that the coding agent will reference during specification, planning, and implementation phases.
-
-### **STEP 2:** Create project specifications
-
-With your project principles established, you can now create the functional specifications. Use the `/speckit.specify` command and then provide the concrete requirements for the project you want to develop.
-
-> [!IMPORTANT]
-> Be as explicit as possible about *what* you are trying to build and *why*. **Do not focus on the tech stack at this point**.
-
-An example prompt:
-
-```text
-Develop Taskify, a team productivity platform. It should allow users to create projects, add team members,
-assign tasks, comment and move tasks between boards in Kanban style. In this initial phase for this feature,
-let's call it "Create Taskify," let's have multiple users but the users will be declared ahead of time, predefined.
-I want five users in two different categories, one product manager and four engineers. Let's create three
-different sample projects. Let's have the standard Kanban columns for the status of each task, such as "To Do,"
-"In Progress," "In Review," and "Done." There will be no login for this application as this is just the very
-first testing thing to ensure that our basic features are set up. For each task in the UI for a task card,
-you should be able to change the current status of the task between the different columns in the Kanban work board.
-You should be able to leave an unlimited number of comments for a particular card. You should be able to, from that task
-card, assign one of the valid users. When you first launch Taskify, it's going to give you a list of the five users to pick
-from. There will be no password required. When you click on a user, you go into the main view, which displays the list of
-projects. When you click on a project, you open the Kanban board for that project. You're going to see the columns.
-You'll be able to drag and drop cards back and forth between different columns. You will see any cards that are
-assigned to you, the currently logged in user, in a different color from all the other ones, so you can quickly
-see yours. You can edit any comments that you make, but you can't edit comments that other people made. You can
-delete any comments that you made, but you can't delete comments anybody else made.
-```
-
-After this prompt is entered, you should see Claude Code kick off the planning and spec drafting process. Claude Code will also trigger some of the built-in scripts to set up the repository.
-
-Once this step is completed, you should have a new branch created (e.g., `001-create-taskify`), as well as a new specification in the `specs/001-create-taskify` directory.
-
-The produced specification should contain a set of user stories and functional requirements, as defined in the template.
-
-At this stage, your project folder contents should resemble the following:
-
-```text
-.
-├── .specify
-│   ├── memory
-│   │   └── constitution.md
-│   ├── scripts
-│   │   └── bash
-│   │       ├── check-prerequisites.sh
-│   │       ├── common.sh
-│   │       ├── create-new-feature.sh
-│   │       ├── setup-plan.sh
-│   │       └── setup-tasks.sh
-│   └── templates
-│       ├── plan-template.md
-│       ├── spec-template.md
-│       └── tasks-template.md
-└── specs
-    └── 001-create-taskify
-        └── spec.md
-```
-
-### **STEP 3:** Functional specification clarification (required before planning)
-
-With the baseline specification created, you can go ahead and clarify any of the requirements that were not captured properly within the first shot attempt.
-
-You should run the structured clarification workflow **before** creating a technical plan to reduce rework downstream.
-
-Preferred order:
-
-1. Use `/speckit.clarify` (structured) – sequential, coverage-based questioning that records answers in a Clarifications section.
-2. Optionally follow up with ad-hoc free-form refinement if something still feels vague.
-
-If you intentionally want to skip clarification (e.g., spike or exploratory prototype), explicitly state that so the agent doesn't block on missing clarifications.
-
-Example free-form refinement prompt (after `/speckit.clarify` if still needed):
-
-```text
-For each sample project or project that you create there should be a variable number of tasks between 5 and 15
-tasks for each one randomly distributed into different states of completion. Make sure that there's at least
-one task in each stage of completion.
-```
-
-You should also ask Claude Code to validate the **Review & Acceptance Checklist**, checking off the things that are validated/pass the requirements, and leave the ones that are not unchecked. The following prompt can be used:
-
-```text
-Read the review and acceptance checklist, and check off each item in the checklist if the feature spec meets the criteria. Leave it empty if it does not.
-```
-
-It's important to use the interaction with Claude Code as an opportunity to clarify and ask questions around the specification - **do not treat its first attempt as final**.
-
-### **STEP 4:** Generate a plan
-
-You can now be specific about the tech stack and other technical requirements. You can use the `/speckit.plan` command that is built into the project template with a prompt like this:
-
-```text
-We are going to generate this using .NET Aspire, using Postgres as the database. The frontend should use
-Blazor server with drag-and-drop task boards, real-time updates. There should be a REST API created with a projects API,
-tasks API, and a notifications API.
-```
-
-The output of this step will include a number of implementation detail documents, with your directory tree resembling this:
-
-```text
-.
-├── CLAUDE.md
-├── .specify
-│   ├── memory
-│   │   └── constitution.md
-│   ├── scripts
-│   │   └── bash
-│   │       ├── check-prerequisites.sh
-│   │       ├── common.sh
-│   │       ├── create-new-feature.sh
-│   │       ├── setup-plan.sh
-│   │       └── setup-tasks.sh
-│   └── templates
-│       ├── CLAUDE-template.md
-│       ├── plan-template.md
-│       ├── spec-template.md
-│       └── tasks-template.md
-└── specs
-    └── 001-create-taskify
-        ├── contracts
-        │   ├── api-spec.json
-        │   └── signalr-spec.md
-        ├── data-model.md
-        ├── plan.md
-        ├── quickstart.md
-        ├── research.md
-        └── spec.md
-```
-
-Check the `research.md` document to ensure that the right tech stack is used, based on your instructions. You can ask Claude Code to refine it if any of the components stand out, or even have it check the locally-installed version of the platform/framework you want to use (e.g., .NET).
-
-Additionally, you might want to ask Claude Code to research details about the chosen tech stack if it's something that is rapidly changing (e.g., .NET Aspire, JS frameworks), with a prompt like this:
-
-```text
-I want you to go through the implementation plan and implementation details, looking for areas that could
-benefit from additional research as .NET Aspire is a rapidly changing library. For those areas that you identify that
-require further research, I want you to update the research document with additional details about the specific
-versions that we are going to be using in this Taskify application and spawn parallel research tasks to clarify
-any details using research from the web.
-```
-
-During this process, you might find that Claude Code gets stuck researching the wrong thing - you can help nudge it in the right direction with a prompt like this:
-
-```text
-I think we need to break this down into a series of steps. First, identify a list of tasks
-that you would need to do during implementation that you're not sure of or would benefit
-from further research. Write down a list of those tasks. And then for each one of these tasks,
-I want you to spin up a separate research task so that the net results is we are researching
-all of those very specific tasks in parallel. What I saw you doing was it looks like you were
-researching .NET Aspire in general and I don't think that's gonna do much for us in this case.
-That's way too untargeted research. The research needs to help you solve a specific targeted question.
-```
-
-> [!NOTE]
-> Claude Code might be over-eager and add components that you did not ask for. Ask it to clarify the rationale and the source of the change.
-
-### **STEP 5:** Have Claude Code validate the plan
-
-With the plan in place, you should have Claude Code run through it to make sure that there are no missing pieces. You can use a prompt like this:
-
-```text
-Now I want you to go and audit the implementation plan and the implementation detail files.
-Read through it with an eye on determining whether or not there is a sequence of tasks that you need
-to be doing that are obvious from reading this. Because I don't know if there's enough here. For example,
-when I look at the core implementation, it would be useful to reference the appropriate places in the implementation
-details where it can find the information as it walks through each step in the core implementation or in the refinement.
-```
-
-This helps refine the implementation plan and helps you avoid potential blind spots that Claude Code missed in its planning cycle. Once the initial refinement pass is complete, ask Claude Code to go through the checklist once more before you can get to the implementation.
-
-You can also ask Claude Code (if you have the [GitHub CLI](https://docs.github.com/en/github-cli/github-cli) installed) to go ahead and create a pull request from your current branch to `main` with a detailed description, to make sure that the effort is properly tracked.
-
-> [!NOTE]
-> Before you have the agent implement it, it's also worth prompting Claude Code to cross-check the details to see if there are any over-engineered pieces (remember - it can be over-eager). If over-engineered components or decisions exist, you can ask Claude Code to resolve them. Ensure that Claude Code follows the constitution in `.specify/memory/constitution.md` as the foundational piece that it must adhere to when establishing the plan.
-
-### **STEP 6:** Generate task breakdown with /speckit.tasks
-
-With the implementation plan validated, you can now break down the plan into specific, actionable tasks that can be executed in the correct order. Use the `/speckit.tasks` command to automatically generate a detailed task breakdown from your implementation plan:
-
-```text
-/speckit.tasks
-```
-
-This step creates a `tasks.md` file in your feature specification directory that contains:
-
-- **Task breakdown organized by user story** - Each user story becomes a separate implementation phase with its own set of tasks
-- **Dependency management** - Tasks are ordered to respect dependencies between components (e.g., models before services, services before endpoints)
-- **Parallel execution markers** - Tasks that can run in parallel are marked with `[P]` to optimize development workflow
-- **File path specifications** - Each task includes the exact file paths where implementation should occur
-- **Test-driven development structure** - If tests are requested, test tasks are included and ordered to be written before implementation
-- **Checkpoint validation** - Each user story phase includes checkpoints to validate independent functionality
-
-The generated tasks.md provides a clear roadmap for the `/speckit.implement` command, ensuring systematic implementation that maintains code quality and allows for incremental delivery of user stories.
-
-### **STEP 7:** Implementation
-
-Once ready, use the `/speckit.implement` command to execute your implementation plan:
-
-```text
-/speckit.implement
-```
-
-The `/speckit.implement` command will:
-
-- Validate that all prerequisites are in place (constitution, spec, plan, and tasks)
-- Parse the task breakdown from `tasks.md`
-- Execute tasks in the correct order, respecting dependencies and parallel execution markers
-- Follow the TDD approach defined in your task plan
-- Provide progress updates and handle errors appropriately
-
-> [!IMPORTANT]
-> The coding agent will execute local CLI commands (such as `dotnet`, `npm`, etc.) - make sure you have the required tools installed on your machine.
-
-Once the implementation is complete, test the application and resolve any runtime errors that may not be visible in CLI logs (e.g., browser console errors). You can copy and paste such errors back to your coding agent for resolution.
-
-</details>
+- **[Quick Start Guide](https://github.github.io/spec-kit/quickstart.html)** - Step-by-step implementation walkthrough
 
 ---
 

docs/community/extensions.md

@@ -51,9 +51,11 @@ 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 | 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) |
+| DocGuard — CDD Enforcement | The only doc-integrity engine with an MCP server, SARIF/JUnit output, and a deterministic zero-LLM core. Validates, scores, and traces documentation against code — 27 validators, stable finding codes, adoption baseline for legacy repos, compliance-evidence reports, 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) |
+| Dotdog | Import GitHub Spec Kit artifacts into local knowledge graphs for validation, analysis, search, and MCP queries. | `docs` | Read+Write | [dotdog](https://github.com/specdog/dotdog) |
 | 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) |
+| Figma Starter | Turns a Figma section's screens into per-screen spec.md files, an app-level user-stories.md, and a build-order.md, then hands off to /speckit.specify | `integration` | Read+Write | [spec-kit-figma-starter](https://github.com/wavemaker/spec-kit-figma-starter) |
 | 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) |
 | Fleet Orchestrator | Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases | `process` | Read+Write | [spec-kit-fleet](https://github.com/sharathsatish/spec-kit-fleet) |
@@ -91,6 +93,7 @@ The following community-contributed extensions are available in [`catalog.commun
 | 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) |
@@ -99,7 +102,7 @@ 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) |
+| Quality Gates (Enforcement Layer) | Deterministic quality enforcement for Spec Kit across agent hooks, git checks, and CI pipelines with one policy file and one verify entrypoint for identical results at every boundary. | `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) |
@@ -133,6 +136,7 @@ The following community-contributed extensions are available in [`catalog.commun
 | Spec Sync | Detect and resolve drift between specs and implementation. AI-assisted resolution with human approval | `docs` | Read+Write | [spec-kit-sync](https://github.com/bgervin/spec-kit-sync) |
 | Spec Trace | Build a requirement → test traceability matrix from spec.md and the test suite — surface untested requirements and orphan tests | `code` | Read+Write | [spec-kit-trace](https://github.com/Quratulain-bilal/spec-kit-trace) |
 | Spec Validate | Comprehension validation, review gating, and approval state for spec-kit artifacts — staged quizzes, peer review SLA, and a hard gate before /speckit.implement | `process` | Read+Write | [spec-kit-spec-validate](https://github.com/aeltayeb/spec-kit-spec-validate) |
+| Spec-Kit BDD | ATDD/BDD extension: convert specs to Gherkin scenarios, scaffold step definitions, and verify acceptance test coverage | `process` | Read+Write | [spec-kit-bdd](https://github.com/RSginer/spec-kit-bdd) |
 | Spec2Cloud | Spec-driven workflow tuned for shipping to Azure | `process` | Read+Write | [spec2cloud](https://github.com/Azure-Samples/Spec2Cloud) |
 | SpecKit Companion | Live spec-driven progress — lifecycle capture, status, resume, and a turbo pipeline profile | `visibility` | Read+Write | [speckit-companion](https://github.com/alfredoperez/speckit-companion) |
 | SpecTest | Auto-generate test scaffolds from spec criteria, map coverage, and find untested requirements | `code` | Read+Write | [spec-kit-spectest](https://github.com/Quratulain-bilal/spec-kit-spectest) |

docs/community/overview.md

@@ -4,7 +4,7 @@ The Spec Kit community builds extensions, presets, bundles, walkthroughs, and co
 
 ## Extensions
 
-Extensions add new capabilities to Spec Kit — domain-specific commands, external tool integrations, quality gates, and more. Over 90 community extensions are available from 50+ authors, covering everything from accessibility governance to multi-agent orchestration.
+Extensions add new capabilities to Spec Kit — domain-specific commands, external tool integrations, quality gates, and more. Over 130 community extensions are available from 70+ authors, covering everything from accessibility governance to multi-agent orchestration.
 
 [Browse community extensions →](extensions.md)
 

docs/index.md

@@ -2,9 +2,9 @@
 
 # GitHub Spec Kit
 
-**Define what to build before building it — with any AI coding agent.**
+**Spec-Driven Development or your own process — step by step or as an automated workflow.**
 
-Spec Kit is a toolkit for [Spec-Driven Development](concepts/sdd.md) (SDD), a methodology that puts specifications at the center of AI-assisted software development. Instead of jumping straight to code, you describe _what_ to build, refine it through structured phases, and let your AI coding agent implement it.
+Spec Kit is an extensible, intent-driven harness that pushes any coding agent beyond code, guiding it across your SDLC or any business process. Use it for [Spec-Driven Development](concepts/sdd.md) (SDD), where you describe _what_ to build and refine it through structured phases. Run it step by step, automate it end to end, or shape a process of your own, keeping intent at the center.
 
 <a href="installation.md" class="btn btn-primary btn-lg">Install Spec Kit</a>&nbsp;
 <a href="quickstart.md" class="btn btn-outline-primary btn-lg">Quick Start</a>
@@ -31,9 +31,9 @@ Define what to build before building it. Rich templates, quality checklists, and
 
 ### Use any coding agent
 
-<span class="pillar-stat">30+ integrations</span> — Copilot, Gemini, Codex, Kilo Code, Zed, Claude, Forge, Kiro, and more. Switch freely between agents with a single command. No lock-in.
+<span class="pillar-stat">35 integrations</span> — Copilot, Gemini, Codex, Kilo Code, Zed, Claude, Forge, Kiro, and more. Switch freely between agents with a single command. No lock-in.
 
-Run `specify init` with your agent of choice and Spec Kit sets up the right command files, context rules, and directory structures automatically. If your agent isn't listed, the `generic` integration is an escape hatch for any tool.
+Run `specify init` with your agent of choice and Spec Kit sets up the right command files and directory structures automatically. If your agent isn't listed, the `generic` integration is an escape hatch for any tool.
 
 <a href="reference/integrations.md" class="pillar-link">See all integrations →</a>
 
@@ -43,17 +43,21 @@ Run `specify init` with your agent of choice and Spec Kit sets up the right comm
 
 ### Make it your own
 
-<span class="pillar-stat">105 community extensions</span> (60+ authors), <span class="pillar-stat">22 presets</span>, and growing. Tune the core process with presets, extend it with extensions, orchestrate it with workflows, or replace it entirely. Build and publish your own.
+<span class="pillar-stat">138 community extensions</span> (70+ authors), <span class="pillar-stat">25 presets</span>, and growing. Tune the core process with presets, extend it with extensions, orchestrate it with workflows, and package it all up as bundles you can share — or replace the process entirely. The process itself lives in these building blocks, so you're never locked to SDD, or even to software.
 
-Including entirely different SDD processes:
+Including entirely different processes:
 
 - **AIDE** — 7-step AI-driven engineering lifecycle
 - **Canon** — baseline-driven workflows (spec-first, code-first, spec-drift)
 - **Product Forge** — product-management-oriented SDD
 - **FX→.NET** — end-to-end .NET Framework migration across 7 phases
 - **MAQA** — multi-agent orchestration with quality assurance gates
+- **Fiction Book Writing** — novels and long-form fiction, from story bible to submission
 
-<a href="community/presets.md" class="pillar-link">Browse community presets →</a>
+<a href="reference/presets.md" class="pillar-link">Presets →</a>&nbsp;&nbsp;
+<a href="reference/extensions.md" class="pillar-link">Extensions →</a>&nbsp;&nbsp;
+<a href="reference/workflows.md" class="pillar-link">Workflows →</a>&nbsp;&nbsp;
+<a href="reference/bundles.md" class="pillar-link">Bundles →</a>
 
 </div>
 
@@ -61,12 +65,12 @@ Including entirely different SDD processes:
 
 ### Integrate into your organization
 
-Works offline, behind firewalls, and on **Windows, macOS, and Linux**. Host your own extension and preset catalogs so your organization controls what gets installed.
+Works offline, behind firewalls, and on **Windows, macOS, and Linux**. Host your own catalogs to curate what integrations, extensions, presets, workflows, and bundles your organization discovers and recommends.
 
 Community extensions like CI Guard and Architecture Guard add compliance gates and governance that fit the way your team already works.
 
-<a href="installation.md" class="pillar-link">Installation guide →</a>&nbsp;&nbsp;
-<a href="reference/extensions.md" class="pillar-link">Extensions reference →</a>
+<a href="install/air-gapped.md" class="pillar-link">Enterprise / Air-Gapped →</a>&nbsp;&nbsp;
+<a href="reference/overview.md" class="pillar-link">Reference →</a>
 
 </div>
 
@@ -78,31 +82,31 @@ Community extensions like CI Guard and Architecture Guard add compliance gates a
 
 ## Built by the community
 
-**200+ contributors** power the Spec Kit ecosystem — from core integrations to entirely new development processes. Anyone can create and publish an extension, preset, or workflow.
+**240+ contributors** power the Spec Kit ecosystem — from core integrations to entirely new processes. Anyone can create and publish an extension, preset, or workflow.
 
 <div class="stats-grid">
   <div class="stat-item">
-    <span class="stat-number">106K+</span>
+    <span class="stat-number">121K+</span>
     <span class="stat-label">GitHub stars</span>
   </div>
   <div class="stat-item">
-    <span class="stat-number">200+</span>
+    <span class="stat-number">240+</span>
     <span class="stat-label">Contributors</span>
   </div>
   <div class="stat-item">
-    <span class="stat-number">30+</span>
+    <span class="stat-number">35</span>
     <span class="stat-label">Integrations</span>
   </div>
   <div class="stat-item">
-    <span class="stat-number">105</span>
+    <span class="stat-number">138</span>
     <span class="stat-label">Extensions</span>
   </div>
   <div class="stat-item">
-    <span class="stat-number">22</span>
+    <span class="stat-number">25</span>
     <span class="stat-label">Presets</span>
   </div>
   <div class="stat-item">
-    <span class="stat-number">4</span>
+    <span class="stat-number">6</span>
     <span class="stat-label">Friends projects</span>
   </div>
 </div>
@@ -143,7 +147,7 @@ Community extensions like CI Guard and Architecture Guard add compliance gates a
 <div class="footer-cta">
 
 ```bash
-uvx --from git+https://github.com/github/spec-kit.git
+uv tool install specify-cli
 specify init my-project --integration copilot
 ```
 
@@ -151,4 +155,4 @@ Ready to start? Follow the [Quick Start Guide](quickstart.md).
 
 </div>
 
-<p class="text-end small text-body-secondary">Last updated: May 27, 2026</p>
+<p class="text-end small text-body-secondary">Last updated: July 16, 2026</p>

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

@@ -11,9 +11,14 @@
 ## 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:
+
+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`):
 
@@ -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/quickstart.md

@@ -1,203 +1,128 @@
 # Quick Start Guide
 
-This guide will help you get started with Spec-Driven Development using Spec Kit.
+This guide will help you get started with Spec-Driven Development using Spec Kit. Throughout, we illustrate each step with a running example: **Taskify**, a small team productivity platform.
 
 > [!NOTE]
-> All automation scripts now provide both Bash (`.sh`) and PowerShell (`.ps1`) variants. The `specify` CLI auto-selects based on OS unless you pass `--script sh|ps`.
+> Automation scripts are provided as both Bash (`.sh`) and PowerShell (`.ps1`) variants. The `specify` CLI auto-selects based on your OS unless you pass `--script sh|ps`.
 
-## Recommended Workflow
+> [!NOTE]
+> Commands are shown here in `/speckit.*` form, but the exact invocation depends on your agent. Some skills-based agents use `$speckit-*` (e.g. Codex, ZCode) or `/skill:speckit-*` (e.g. Kimi). Use whichever form your agent exposes — the steps are otherwise identical.
+
+## Recommended Process
 
 > [!TIP]
-> **Context Awareness**: Spec Kit commands automatically detect the active feature based on your current Git branch (e.g., `001-feature-name`). To switch between different specifications, simply switch Git branches.
+> **Context Awareness**: Spec Kit tracks the active feature by the feature directory recorded in `.specify/feature.json` (overridable with the `SPECIFY_FEATURE_DIRECTORY` environment variable). Commands resolve the feature from that state, **not** from the checked-out Git branch — no Git required. The opt-in **git** extension adds numbered feature branches (e.g. `001-feature-name`) for organizing work in version control, but the active feature is still whichever directory that state points to; `git checkout` alone does not change it. To point commands at a different feature, update `.specify/feature.json` (or set `SPECIFY_FEATURE_DIRECTORY`).
 
-After installing Spec Kit and defining your project constitution, quick experiments can use the lean feature path: `/speckit.specify` -> `/speckit.plan` -> `/speckit.tasks` -> `/speckit.implement`. For production features or any work with meaningful ambiguity, treat `/speckit.clarify`, `/speckit.checklist`, and `/speckit.analyze` as regular quality gates:
+After installing Spec Kit, each command below is a step in the process. Two paths are common:
+
+**Shorter path** — for smaller features:
+
+1. `/speckit.specify`
+2. `/speckit.plan`
+3. `/speckit.tasks`
+4. `/speckit.implement`
+5. `/speckit.converge`
+
+**Full path** — for production features, adding `/speckit.clarify`, `/speckit.checklist`, and `/speckit.analyze` as quality gates:
+
+1. `/speckit.constitution`
+2. `/speckit.specify`
+3. `/speckit.clarify`
+4. `/speckit.plan`
+5. `/speckit.checklist`
+6. `/speckit.tasks`
+7. `/speckit.analyze`
+8. `/speckit.implement`
+9. `/speckit.converge`
+
+### Install Specify
+
+**In your terminal**, install the CLI from PyPI (requires [uv](install/uv.md)), then initialize your project:
+
+```bash
+uv tool install specify-cli
+specify init taskify   # or: specify init .   to use the current directory
+```
+
+`init` lets you pick your coding agent interactively, or pass it explicitly with `--integration` (e.g. `--integration copilot`).
+
+> [!NOTE]
+> Prefer `pipx`, one-time `uvx` runs, a pinned release, or an offline/air-gapped setup? See the [Installation Guide](installation.md) for all supported methods.
+
+### Step 1: `/speckit.constitution` — set the ground rules
+
+Establishes the project's guiding principles, which every later step is evaluated against. Run it once up front, passing your principles as arguments.
 
 ```text
-/speckit.constitution -> /speckit.specify -> /speckit.clarify -> /speckit.plan -> /speckit.checklist -> /speckit.tasks -> /speckit.analyze -> /speckit.implement -> /speckit.converge
-```
-
-Use `/speckit.clarify` to reduce requirement ambiguity before planning, `/speckit.checklist` (after `/speckit.plan`) to generate quality checklists that validate requirements completeness, clarity, and consistency, and `/speckit.analyze` to check spec/plan/task consistency before implementation starts. You can repeat `/speckit.analyze` after implementation as an extra review, but keep the first analysis before `/speckit.implement` so gaps are caught while the plan and tasks can still be adjusted. Finally, run `/speckit.converge` after implementation to verify all planned work is complete and generate tasks for any remaining gaps. If `/speckit.converge` appends new tasks, run `/speckit.implement` again (and converge again) until it reports that the feature has converged.
-
-### Step 1: Install Specify
-
-**In your terminal**, run the `specify` CLI command to initialize your project:
-
-```bash
-# Create a new project directory
-uvx --from git+https://github.com/github/spec-kit.git specify init <PROJECT_NAME>
-
-# OR initialize in the current directory
-uvx --from git+https://github.com/github/spec-kit.git specify init .
-```
-
-> [!NOTE]
-> You can also install the CLI persistently with `pipx`:
->
-> ```bash
-> pipx install git+https://github.com/github/spec-kit.git
-> ```
->
-> After installing with `pipx`, run `specify` directly instead of `uvx --from ... specify`, for example:
->
-> ```bash
-> specify init <PROJECT_NAME>
-> specify init .
-> ```
-
-Pick script type explicitly (optional):
-
-```bash
-uvx --from git+https://github.com/github/spec-kit.git specify init <PROJECT_NAME> --script ps  # Force PowerShell
-uvx --from git+https://github.com/github/spec-kit.git specify init <PROJECT_NAME> --script sh  # Force POSIX shell
-```
-
-### Step 2: Define Your Constitution
-
-**In your coding agent's chat interface**, use the `/speckit.constitution` slash command to establish the core rules and principles for your project. You should provide your project's specific principles as arguments.
-
-```markdown
-/speckit.constitution This project follows a "Library-First" approach. All features must be implemented as standalone libraries first. We use TDD strictly. We prefer functional programming patterns.
-```
-
-### Step 3: Create the Spec
-
-**In the chat**, use the `/speckit.specify` slash command to describe what you want to build. Focus on the **what** and **why**, not the tech stack.
-
-```markdown
-/speckit.specify Build an application that can help me organize my photos in separate photo albums. Albums are grouped by date and can be re-organized by dragging and dropping on the main page. Albums are never in other nested albums. Within each album, photos are previewed in a tile-like interface.
-```
-
-### Step 4: Refine and Validate the Spec
-
-**In the chat**, use the `/speckit.clarify` slash command to identify and resolve ambiguities in your specification. You can provide specific focus areas as arguments.
-
-```bash
-/speckit.clarify Focus on security and performance requirements.
-```
-
-### Step 5: Create a Technical Implementation Plan
-
-**In the chat**, use the `/speckit.plan` slash command to provide your tech stack and architecture choices.
-
-```markdown
-/speckit.plan The application uses Vite with minimal number of libraries. Use vanilla HTML, CSS, and JavaScript as much as possible. Images are not uploaded anywhere and metadata is stored in a local SQLite database.
-```
-
-Then generate quality checklists with `/speckit.checklist` once the plan exists:
-
-```bash
-/speckit.checklist
-```
-
-### Step 6: Break Down, Analyze, and Implement
-
-**In the chat**, use the `/speckit.tasks` slash command to create an actionable task list.
-
-```markdown
-/speckit.tasks
-```
-
-Validate cross-artifact consistency with `/speckit.analyze` before implementation:
-
-```markdown
-/speckit.analyze
-```
-
-Use the `/speckit.implement` slash command to execute the plan.
-
-```markdown
-/speckit.implement
-```
-
-> [!TIP]
-> **Phased Implementation**: For complex projects, implement in phases to avoid overwhelming the agent's context. Start with core functionality, validate it works, then add features incrementally.
-
-## Detailed Example: Building Taskify
-
-Here's a complete example of building a team productivity platform:
-
-### Step 1: Define Constitution
-
-Initialize the project's constitution to set ground rules:
-
-```markdown
 /speckit.constitution Taskify is a "Security-First" application. All user inputs must be validated. We use a microservices architecture. Code must be fully documented.
 ```
 
-### Step 2: Define Requirements with `/speckit.specify`
+### Step 2: `/speckit.specify` — describe what to build
+
+Creates the feature specification from a natural-language description. Focus on the **what** and **why**, not the tech stack.
 
 ```text
-/speckit.specify Develop Taskify, a team productivity platform. It should allow users to create projects, add team members,
-assign tasks, comment and move tasks between boards in Kanban style. In this initial phase for this feature,
-let's call it "Create Taskify," let's have multiple users but the users will be declared ahead of time, predefined.
-I want five users in two different categories, one product manager and four engineers. Let's create three
-different sample projects. Let's have the standard Kanban columns for the status of each task, such as "To Do,"
-"In Progress," "In Review," and "Done." There will be no login for this application as this is just the very
-first testing thing to ensure that our basic features are set up.
+/speckit.specify Develop Taskify, a team productivity platform where predefined users create projects, assign tasks, comment, and move tasks across Kanban columns (To Do, In Progress, In Review, Done). Five users (one product manager, four engineers), three sample projects, no login for this first phase.
 ```
 
-### Step 3: Refine the Specification
+### Step 3: `/speckit.clarify` — resolve ambiguities
 
-Use the `/speckit.clarify` command to interactively resolve any ambiguities in your specification. You can also provide specific details you want to ensure are included.
+Asks targeted questions about anything underspecified and folds your answers back into the spec, so you're not planning on top of ambiguity. Run it before planning, optionally with a focus area.
 
-```bash
-/speckit.clarify I want to clarify the task card details. For each task in the UI for a task card, you should be able to change the current status of the task between the different columns in the Kanban work board. You should be able to leave an unlimited number of comments for a particular card. You should be able to, from that task card, assign one of the valid users.
+```text
+/speckit.clarify Focus on task card behavior — status changes, comment permissions, and user assignment.
 ```
 
-You can continue to refine the spec with more details using `/speckit.clarify`:
+### Step 4: `/speckit.plan` — choose the tech stack
 
-```bash
-/speckit.clarify When you first launch Taskify, it's going to give you a list of the five users to pick from. There will be no password required. When you click on a user, you go into the main view, which displays the list of projects. When you click on a project, you open the Kanban board for that project. You're going to see the columns. You'll be able to drag and drop cards back and forth between different columns. You will see any cards that are assigned to you, the currently logged in user, in a different color from all the other ones, so you can quickly see yours. You can edit any comments that you make, but you can't edit comments that other people made. You can delete any comments that you made, but you can't delete comments anybody else made.
+Generates the design artifacts from the spec. This is where implementation detail belongs — provide your tech stack and architecture.
+
+```text
+/speckit.plan Use .NET Aspire with Postgres. The frontend is Blazor Server with drag-and-drop boards and real-time updates. Expose REST APIs for projects, tasks, and notifications.
 ```
 
-### Step 4: Generate Technical Plan with `/speckit.plan`
+### Step 5: `/speckit.checklist` — validate the spec
 
-Be specific about your tech stack and technical requirements:
+Generates a quality checklist — "unit tests for your requirements" — to confirm the spec is complete, clear, and consistent before you break the work down.
 
-```bash
-/speckit.plan We are going to generate this using .NET Aspire, using Postgres as the database. The frontend should use Blazor server with drag-and-drop task boards, real-time updates. There should be a REST API created with a projects API, tasks API, and a notifications API.
-```
-
-### Step 5: Validate the Spec
-
-Generate quality checklists to validate the specification using the `/speckit.checklist` command:
-
-```bash
+```text
 /speckit.checklist
 ```
 
-### Step 6: Define Tasks
+### Step 6: `/speckit.tasks` — break the work down
 
-Generate an actionable task list using the `/speckit.tasks` command:
+Generates an actionable, dependency-ordered `tasks.md` from the design artifacts.
 
-```bash
+```text
 /speckit.tasks
 ```
 
-### Step 7: Validate and Implement
+### Step 7: `/speckit.analyze` — check consistency
 
-Have your coding agent audit the spec, plan, and tasks with `/speckit.analyze` before implementation:
+Reports conflicts, gaps, and ambiguities across `spec.md`, `plan.md`, and `tasks.md`. It's read-only — if it flags issues, fix them at the source and re-run before implementing.
 
-```bash
+```text
 /speckit.analyze
 ```
 
-Finally, implement the solution:
+### Step 8: `/speckit.implement` — build it
 
-```bash
+Executes the tasks in `tasks.md` in dependency order. Run it once to build everything, or scope it to one phase at a time for large features.
+
+```text
 /speckit.implement
 ```
 
-### Step 8: Converge
+### Step 9: `/speckit.converge` — verify completeness
 
-Run the `/speckit.converge` command after implementation to assess the current codebase against the feature's artifacts and append any remaining unbuilt work as new tasks to `tasks.md`. If the command appends new tasks, run `/speckit.implement` again to complete them, and repeat the converge step until the feature is fully complete.
+Checks the codebase against the spec, plan, and tasks. If it finds gaps, it appends new tasks to `tasks.md`; run `/speckit.implement` and converge again until it reports converged. Otherwise you're done — proceed to review or open a PR.
 
-```bash
+```text
 /speckit.converge
 ```
 
 > [!TIP]
-> **Phased Implementation**: For large projects like Taskify, consider implementing in phases (e.g., Phase 1: Basic project/task structure, Phase 2: Kanban functionality, Phase 3: Comments and assignments). This prevents context saturation and allows for validation at each stage.
+> For a full reference on each command — arguments, output, phased implementation, and how they interact — see [Agentic SDD](reference/agentic-sdd.md).
 
 ## Key Principles
 
@@ -209,6 +134,7 @@ Run the `/speckit.converge` command after implementation to assess the current c
 
 ## Next Steps
 
+- See the [Agentic SDD](reference/agentic-sdd.md) reference for full detail on every command
 - Read the [complete methodology](https://github.com/github/spec-kit/blob/main/spec-driven.md) for in-depth guidance
 - Check out [more examples](https://github.com/github/spec-kit/tree/main/templates) in the repository
 - Explore the [source code on GitHub](https://github.com/github/spec-kit)

docs/reference/agentic-bugfix.md

@@ -0,0 +1,52 @@
+# Agentic Bug Fix
+
+The **bug** extension adds a three-step bug triage process — assess, fix, and validate — that your coding agent runs alongside the core [Agentic SDD](agentic-sdd.md) process. Each bug lives in its own directory under `.specify/bugs/<slug>/`, with one Markdown report per stage.
+
+> [!NOTE]
+> Commands are written in `/speckit.bug.*` form throughout this page. The exact invocation depends on your agent — some skills-based agents use `$speckit-bug-*` (e.g. Codex, ZCode) or `/skill:speckit-bug-*` (e.g. Kimi). Substitute the form your agent exposes.
+
+The bug extension is a bundled, opt-in extension. Install it before using these commands:
+
+```bash
+specify extension add bug
+```
+
+The three commands share a single handle — the **slug**, the per-bug directory name under `.specify/bugs/`. Supply it with `slug=<name>`; if omitted, `/speckit.bug.assess` asks for one (or generates a unique one in automated mode). Slugs are normalized to lowercase kebab-case. If an assessment already exists for a slug, an interactive run asks before overwriting it, while an automated run refuses and picks a new unique slug instead.
+
+```text
+/speckit.bug.assess -> /speckit.bug.fix -> /speckit.bug.test
+```
+
+## `/speckit.bug.assess`
+
+Triages a bug report — pasted text (such as a stack trace) or a URL (such as a GitHub issue) — against the codebase: it judges whether the report is a real bug, locates the suspected code paths, and proposes a remediation. This command is **read-only**: it writes only `assessment.md` and never modifies source code.
+
+```text
+/speckit.bug.assess "TypeError: cannot read properties of undefined (reading 'token') at /auth/callback"
+```
+
+```text
+/speckit.bug.assess https://github.com/example/repo/issues/1234 slug=callback-token
+```
+
+Output: `.specify/bugs/<slug>/assessment.md`.
+
+## `/speckit.bug.fix`
+
+Applies the remediation described in the assessment and records exactly what changed. This is the **only** bug command that edits source code, and it stays within the files listed in the assessment unless new evidence requires expanding scope (logged under **Deviations from Assessment**).
+
+```text
+/speckit.bug.fix slug=callback-token
+```
+
+Output: `.specify/bugs/<slug>/fix.md`.
+
+## `/speckit.bug.test`
+
+Validates the fix by re-running the reproduction and any added tests, then records the verification result — one of `verified`, `partial`, or `failed`. Like `assess`, it is **read-only** with respect to source code. Verdicts are never over-claimed: if the assessment listed a reproduction that wasn't actually exercised, the overall result is downgraded to `partial` rather than reported as `verified`.
+
+```text
+/speckit.bug.test slug=callback-token
+```
+
+Output: `.specify/bugs/<slug>/test.md`.

docs/reference/agentic-sdd.md

@@ -0,0 +1,115 @@
+# Agentic SDD
+
+The `/speckit.*` slash commands drive the core Spec-Driven Development (SDD) process — an **agentic process** your coding agent runs step by step. For a guided, end-to-end run see the [Quick Start Guide](../quickstart.md); this page is the detailed reference for each command — including arguments, output, and how they interact. For the philosophy behind the process, see [What is SDD?](../concepts/sdd.md). For bug triage, see [Agentic Bug Fix](agentic-bugfix.md).
+
+The commands are designed to run in order, but only `/speckit.specify` is strictly required before `/speckit.plan`. The clarify, checklist, and analyze commands are quality gates you add for anything with meaningful ambiguity.
+
+> [!NOTE]
+> Commands are written in `/speckit.*` form throughout this page. The exact invocation depends on your agent — some skills-based agents use `$speckit-*` (e.g. Codex, ZCode) or `/skill:speckit-*` (e.g. Kimi). Substitute the form your agent exposes.
+
+```text
+/speckit.constitution -> /speckit.specify -> /speckit.clarify -> /speckit.plan -> /speckit.checklist -> /speckit.tasks -> /speckit.analyze -> /speckit.implement -> /speckit.converge
+```
+
+## `/speckit.constitution`
+
+Creates or updates the project **constitution** — the guiding principles that every later phase is evaluated against — and keeps dependent templates in sync. Run it once up front and update it whenever your principles change. Pass the principles as arguments.
+
+```text
+/speckit.constitution This project follows a "Library-First" approach. All features must be implemented as standalone libraries first. We use TDD strictly. We prefer functional programming patterns.
+```
+
+## `/speckit.specify`
+
+Creates or updates the feature **specification** from a natural-language description. Focus on the **what** and **why** — the user-facing behavior and goals — not the tech stack, which belongs in `/speckit.plan`.
+
+```text
+/speckit.specify Build an application that helps me organize photos into albums grouped by date, re-orderable by drag-and-drop on the main page, with a tile preview inside each album.
+```
+
+## `/speckit.clarify`
+
+Asks up to five targeted questions about underspecified areas of the current spec and encodes your answers back into `spec.md`. Run it as many times as needed before planning, each time tackling a different area. Optionally pass a focus area as an argument.
+
+```text
+/speckit.clarify Focus on the task card behavior: status changes, comment limits, and who can be assigned.
+```
+
+Clarifying before planning keeps you from designing on top of ambiguity. If `/speckit.analyze` later surfaces requirement gaps, come back and run `/speckit.clarify` (or `/speckit.specify`) again.
+
+## `/speckit.plan`
+
+Runs the planning process to generate design artifacts from the spec. This is where implementation detail belongs — provide your tech stack, architecture, and technical constraints as arguments.
+
+```text
+/speckit.plan Use .NET Aspire with Postgres. The frontend is Blazor Server with drag-and-drop boards and real-time updates. Expose REST APIs for projects, tasks, and notifications.
+```
+
+## `/speckit.checklist`
+
+Generates a quality checklist for the feature — think of it as **"unit tests for your requirements."** Rather than testing code, it checks whether the spec itself is complete, clear, unambiguous, and consistent (for example: "Are the drag-and-drop rules defined for every column?", "Is behavior specified for a deleted assigned user?").
+
+Run it with no arguments for a broad pass, or pass a focus area to target one aspect:
+
+```text
+/speckit.checklist
+```
+
+```text
+/speckit.checklist Focus on the Kanban board interactions and comment permissions.
+```
+
+Review the generated checklist. If it surfaces gaps, loop back to `/speckit.clarify` or `/speckit.specify` to tighten the spec before breaking the work down.
+
+## `/speckit.tasks`
+
+Generates an actionable, dependency-ordered `tasks.md` from the design artifacts. Tasks are organized into phases: **Setup**, **Foundational** (blocking prerequisites), then **one phase per user story** in priority order, and a final **Polish** phase for cross-cutting concerns. Tests are generated within a user story's phase when requested rather than as a separate phase, and tasks are marked for parallel execution where possible.
+
+```text
+/speckit.tasks
+```
+
+## `/speckit.analyze`
+
+Performs a **read-only** cross-artifact consistency and quality analysis across `spec.md`, `plan.md`, and `tasks.md`, reporting conflicts, gaps, and ambiguities (for example a task with no matching requirement, or a plan choice that contradicts the spec). It never edits files — it produces a report and can optionally suggest remediations for you to approve.
+
+```text
+/speckit.analyze
+```
+
+Run it before implementing, while the artifacts can still be adjusted cheaply. If it surfaces issues, **return to the earlier step that owns them** and fix them at the source — `/speckit.specify` or `/speckit.clarify` for requirement problems, `/speckit.plan` for design problems, `/speckit.tasks` to regenerate the task list — then re-run `/speckit.analyze` until it comes back clean. You can also run `/speckit.analyze` again after implementation as an extra review.
+
+## `/speckit.implement`
+
+Executes the tasks in `tasks.md`, running each phase in dependency order and respecting parallel markers.
+
+For a small feature, run it once to build everything:
+
+```text
+/speckit.implement
+```
+
+For a large feature, work in stages to avoid overwhelming the agent's context — scope each run with an argument, validate the result, then continue:
+
+```text
+/speckit.implement Implement only the Setup and Foundational phases: project scaffolding and the project/task data model with basic CRUD. Stop before the user-story features.
+```
+
+```text
+/speckit.implement Now implement the Kanban board user story: drag-and-drop between columns.
+```
+
+Verify each stage works before moving to the next.
+
+## `/speckit.converge`
+
+Assesses the codebase against the feature's spec, plan, and tasks to confirm nothing was missed. It is **append-only**: it never edits or deletes code, and its only possible write is adding tasks to `tasks.md`. Run it only after `/speckit.implement` has run on the current `tasks.md`.
+
+```text
+/speckit.converge
+```
+
+It first prints a severity-graded findings summary, then resolves to one of two outcomes:
+
+- **Converged** — no gaps found. `tasks.md` is left byte-for-byte unchanged and you'll see a clean result like `✅ Converged — the implementation satisfies the spec, plan, and tasks.` You're done; proceed to review or open a PR.
+- **Tasks appended** — gaps found. Converge appends them as new tasks under a Convergence section in `tasks.md` and tells you how many. Run `/speckit.implement` again to complete them, then `/speckit.converge` once more. Each pass finds fewer items; repeat until it reports converged.

docs/reference/extensions.md

@@ -171,6 +171,63 @@ To set up configuration for a newly installed extension, copy the template:
 cp .specify/extensions/<ext>/<ext>-config.template.yml \
    .specify/extensions/<ext>/<ext>-config.yml
 ```
+## Project Extension and Hook Configuration
+
+Spec Kit stores project-level extension registration and hook configuration in:
+
+```text
+.specify/extensions.yml
+```
+The file contains installed extensions, global settings, and hooks that are surfaced before or after Spec Kit commands.
+
+```yaml
+installed:
+  - git
+  - my-extension
+
+settings:
+  auto_execute_hooks: true
+
+hooks:
+  before_implement:
+    - extension: git
+      command: speckit.git.commit
+      enabled: true
+      optional: true
+      priority: 10
+      prompt: "Commit outstanding changes before implementation?"
+      description: "Auto-commit before implementation"
+
+  after_implement:
+    - extension: my-extension
+      command: speckit.my-extension.verify
+      enabled: true
+      optional: false
+      priority: 5
+      description: "Run verification after implementation"
+```
+
+### Configuration fields
+
+The top-level `installed` list records extensions installed in the project. The `settings` mapping stores project-wide extension settings, and `hooks` groups hook registrations by event.
+
+`auto_execute_hooks` defaults to `true`, but is currently reserved and is not consulted when hooks are surfaced or invoked.
+
+Each hook entry supports the following fields:
+
+| Field | Description |
+| --- | --- |
+| `extension` | ID of the extension that registered the hook. |
+| `command` | Extension command associated with the hook. |
+| `enabled` | Whether the hook is active. Hooks with `enabled: false` are skipped. |
+| `optional` | Whether the hook is optional. If `true`, the hook is presented with its `prompt` and can be skipped; if `false`, the hook is emitted as an automatic hook (includes `EXECUTE_COMMAND` markers). |
+| `priority` | Priority metadata for the hook. Values must be integers >= 1; invalid values fall back to the default priority `10`. Current command templates surface hooks in their configured YAML order and do not sort them by `priority`. |
+| `prompt` | Message shown when asking whether to run an optional hook. |
+| `description` | Human-readable explanation of what the hook does. |
+| `condition` | Optional expression evaluated by `HookExecutor` (using `config.<path>` or `env.<VAR>` with `is set`, `==`, or `!=`). Current command templates do not evaluate conditions and skip hooks with a non-empty condition. |
+Hook event names identify when a hook is invoked. They generally use `before_<command>` or `after_<command>`, such as `before_implement`, `after_implement`, `before_tasks`, and `after_tasks`.
+
+`HookExecutor.get_hooks_for_event()` returns hooks ordered by `priority`, with lower values first. However, current command templates read hook lists directly and surface them in their configured YAML order rather than using priority ordering.
 
 ## FAQ
 

docs/reference/integrations.md

@@ -1,6 +1,6 @@
 # Supported AI Coding Agent Integrations
 
-The Specify CLI supports a wide range of AI coding agents. When you run `specify init`, the CLI sets up the appropriate command files, context rules, and directory structures for your chosen AI coding agent — so you can start using Spec-Driven Development immediately, regardless of which tool you prefer.
+The Specify CLI supports a wide range of AI coding agents. When you run `specify init`, the CLI sets up the appropriate command files and directory structures for your chosen AI coding agent — so you can start using Spec-Driven Development immediately, regardless of which tool you prefer.
 
 ## Supported AI Coding Agents
 
@@ -20,6 +20,7 @@ The Specify CLI supports a wide range of AI coding agents. When you run `specify
 | [Gemini CLI](https://github.com/google-gemini/gemini-cli)                            | `gemini`         |                                                                                                                                           |
 | [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/`                                                                                              |
+| [Grok Build](https://docs.x.ai/build/overview)                                       | `grok`           | Skills-based integration; installs skills into `.grok/skills` and invokes them as `/speckit-<command>`                                    |
 | [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                                                                                                                           |
 | [Junie](https://junie.jetbrains.com/)                                                | `junie`          |                                                                                                                                           |
@@ -249,7 +250,11 @@ Spec Kit tracks one default integration in `.specify/integration.json` with `def
 
 ### Which integrations are multi-install safe?
 
-An integration is multi-install safe when it uses isolated agent directories, a dedicated context file that does not collide with another safe integration, stable command invocation settings, and a separate install manifest. Shared Spec Kit templates remain aligned to the single default integration.
+An integration is multi-install safe when it uses a static, unique agent root and command directory, stable command invocation settings, and a separate install manifest whose managed files do not overlap another safe integration. Registry tests enforce those path and manifest invariants. Shared Spec Kit templates remain aligned to the single default integration.
+
+The Isolation column below lists paths Spec Kit manages for that integration (skills/commands roots and any integration-owned rule files). It is not a full inventory of every file an agent may read.
+
+**Agent-context defaults are separate.** The optional agent-context extension maps each integration to a default context file in `extensions/agent-context/agent-context-defaults.json`. Those defaults are independent of multi-install safety: several agents may share a root file such as `AGENTS.md` when the extension is enabled. Multi-install safety does not require a unique context file per safe integration.
 
 The currently declared multi-install safe integrations are:
 
@@ -263,6 +268,7 @@ The currently declared multi-install safe integrations are:
 | `cursor-agent` | `.cursor/skills`, `.cursor/rules/specify-rules.mdc` |
 | `firebender` | `.firebender/commands`, `.firebender/rules/specify-rules.mdc` |
 | `gemini` | `.gemini/commands`, `GEMINI.md` |
+| `grok` | `.grok/skills` |
 | `junie` | `.junie/commands`, `.junie/AGENTS.md` |
 | `kilocode` | `.kilocode/workflows`, `.kilocode/rules/specify-rules.md` |
 | `qodercli` | `.qoder/commands`, `QODER.md` |
@@ -272,7 +278,7 @@ The currently declared multi-install safe integrations are:
 | `trae` | `.trae/skills`, `.trae/rules/project_rules.md` |
 | `zcode` | `.zcode/skills`, `ZCODE.md` |
 
-Integrations that share a context file or command directory with another integration, require dynamic install paths such as `--commands-dir`, or merge shared tool settings are not declared safe by default. They can still be installed alongside another integration with `--force`.
+Integrations that share a command directory with another integration, require dynamic install paths such as `--commands-dir`, or merge shared tool settings are not declared safe by default. They can still be installed alongside another integration with `--force`.
 
 ### What happens to my changes when I uninstall or switch?
 

docs/reference/overview.md

@@ -1,6 +1,6 @@
-# CLI Reference
+# Reference
 
-The Specify CLI (`specify`) manages the full lifecycle of Spec-Driven Development — from project initialization to workflow automation.
+The Specify CLI (`specify`) manages the full lifecycle of Spec-Driven Development — from project initialization to workflow automation. This section is the detailed reference for the CLI's commands and primitives, plus the agentic `/speckit.*` processes your coding agent runs.
 
 ## Core Commands
 
@@ -10,7 +10,7 @@ The foundational commands for creating and managing Spec Kit projects. Initializ
 
 ## Integrations
 
-Integrations connect Spec Kit to your AI coding agent. Each integration sets up the appropriate command files, context rules, and directory structures for a specific agent. Only one integration is active per project at a time, and you can switch between them at any point.
+Integrations connect Spec Kit to your AI coding agent. Each integration sets up the appropriate command files and directory structures for a specific agent. Only one integration is active per project at a time, and you can switch between them at any point.
 
 [Integrations reference →](integrations.md)
 
@@ -37,3 +37,19 @@ Workflows automate multi-step Spec-Driven Development processes into repeatable
 Bundles compose existing extensions, presets, workflows, and steps into a single, versioned, installable unit. Rather than adding new behavior, a bundle curates a stack of primitives — everything a team or role needs — and installs it in one step through each component's own machinery, with version pinning, conflict checks, and provenance tracking for clean updates and removal.
 
 [Bundles reference →](bundles.md)
+
+## Agentic Commands
+
+The sections above cover primitives managed by the `specify` CLI. The following are the `/speckit.*` slash commands your coding agent runs step by step inside the editor — the agentic processes built on top of that foundation.
+
+### Agentic SDD
+
+The `/speckit.*` slash commands that drive the core Spec-Driven Development process your coding agent runs step by step: constitution, specify, clarify, plan, checklist, tasks, analyze, implement, and converge. Run them in order, adding the clarify/checklist/analyze quality gates for anything with meaningful ambiguity.
+
+[Agentic SDD reference →](agentic-sdd.md)
+
+### Agentic Bug Fix
+
+The bundled **bug** extension adds a three-step bug triage process — assess, fix, and validate — with each bug tracked in its own directory under `.specify/bugs/`. Install it with `specify extension add bug`.
+
+[Agentic Bug Fix reference →](agentic-bugfix.md)

docs/reference/workflows.md

@@ -305,6 +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`.
 
@@ -316,6 +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)
@@ -37,6 +39,10 @@
       href: reference/workflows.md
     - name: Bundles
       href: reference/bundles.md
+    - name: Agentic SDD
+      href: reference/agentic-sdd.md
+    - name: Agentic Bug Fix
+      href: reference/agentic-bugfix.md
     - name: Authentication
       href: reference/authentication.md
 

extensions/agent-context/agent-context-defaults.json

@@ -17,6 +17,7 @@
     "gemini": "GEMINI.md",
     "generic": "AGENTS.md",
     "goose": "AGENTS.md",
+    "grok": "AGENTS.md",
     "hermes": "AGENTS.md",
     "junie": ".junie/AGENTS.md",
     "kilocode": ".kilocode/rules/specify-rules.md",

extensions/catalog.community.json

@@ -1,6 +1,6 @@
 {
   "schema_version": "1.0",
-  "updated_at": "2026-07-13T00:00:00Z",
+  "updated_at": "2026-07-16T00:00:00Z",
   "catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json",
   "extensions": {
     "aide": {
@@ -395,6 +395,66 @@
       "created_at": "2026-03-03T00:00:00Z",
       "updated_at": "2026-03-03T00:00:00Z"
     },
+    "bdd": {
+      "name": "Spec-Kit BDD",
+      "id": "bdd",
+      "description": "ATDD/BDD extension: convert specs to Gherkin scenarios, scaffold step definitions, and verify acceptance test coverage.",
+      "author": "RSginer",
+      "version": "1.0.2",
+      "download_url": "https://github.com/RSginer/spec-kit-bdd/archive/refs/tags/v1.0.2.zip",
+      "repository": "https://github.com/RSginer/spec-kit-bdd",
+      "homepage": "https://github.com/RSginer/spec-kit-bdd",
+      "documentation": "https://github.com/RSginer/spec-kit-bdd/blob/main/docs/usage.md",
+      "changelog": "https://github.com/RSginer/spec-kit-bdd/releases",
+      "license": "MIT",
+      "category": "process",
+      "effect": "read-write",
+      "requires": {
+        "speckit_version": ">=0.2.0",
+        "tools": [
+          {
+            "name": "pytest-bdd",
+            "required": false
+          },
+          {
+            "name": "behave",
+            "required": false
+          },
+          {
+            "name": "@cucumber/cucumber",
+            "required": false
+          },
+          {
+            "name": "cucumber",
+            "required": false
+          },
+          {
+            "name": "io.cucumber",
+            "required": false
+          },
+          {
+            "name": "SpecFlow",
+            "required": false
+          }
+        ]
+      },
+      "provides": {
+        "commands": 3,
+        "hooks": 2
+      },
+      "tags": [
+        "bdd",
+        "gherkin",
+        "atdd",
+        "acceptance-testing",
+        "tdd"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-15T00:00:00Z",
+      "updated_at": "2026-07-15T00:00:00Z"
+    },
     "blueprint": {
       "name": "Blueprint",
       "id": "blueprint",
@@ -809,8 +869,8 @@
       "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 +895,7 @@
       "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 +1166,10 @@
     "docguard": {
       "name": "DocGuard — CDD Enforcement",
       "id": "docguard",
-      "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.",
+      "description": "The only doc-integrity engine with an MCP server, SARIF/JUnit output, and a deterministic zero-LLM core. Validates, scores, and traces documentation against code — 27 validators, stable finding codes, adoption baseline for legacy repos, compliance-evidence reports, GitHub Action with PR annotations, spec-kit hooks. Pure Node.js, one pinned dep.",
       "author": "raccioly",
-      "version": "0.32.0",
-      "download_url": "https://github.com/raccioly/docguard/releases/download/v0.32.0/spec-kit-docguard-v0.32.0.zip",
+      "version": "0.33.0",
+      "download_url": "https://github.com/raccioly/docguard/releases/download/v0.33.0/spec-kit-docguard-v0.33.0.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",
@@ -1153,7 +1213,7 @@
       "downloads": 0,
       "stars": 0,
       "created_at": "2026-03-13T00:00:00Z",
-      "updated_at": "2026-07-13T00:00:00Z"
+      "updated_at": "2026-07-16T00:00:00Z"
     },
     "doctor": {
       "name": "Project Health Check",
@@ -1188,6 +1248,47 @@
       "created_at": "2026-03-13T00:00:00Z",
       "updated_at": "2026-03-13T00:00:00Z"
     },
+    "dotdog": {
+      "name": "Dotdog",
+      "id": "dotdog",
+      "description": "Import GitHub Spec Kit artifacts into local knowledge graphs for validation, analysis, search, and MCP queries.",
+      "author": "specdog",
+      "version": "0.9.0",
+      "download_url": "https://github.com/specdog/dotdog/releases/download/v0.9.0/dotdog-spec-kit-extension-v0.9.0.zip",
+      "repository": "https://github.com/specdog/dotdog",
+      "homepage": "https://specdog.github.io/dotdog",
+      "documentation": "https://github.com/specdog/dotdog/blob/main/docs/spec-kit-extension.md",
+      "changelog": "https://github.com/specdog/dotdog/blob/main/CHANGELOG.md",
+      "license": "MIT",
+      "category": "docs",
+      "effect": "read-write",
+      "requires": {
+        "speckit_version": ">=0.12.0",
+        "tools": [
+          {
+            "name": "dotdog",
+            "version": ">=0.9.0",
+            "required": true
+          }
+        ]
+      },
+      "provides": {
+        "commands": 3,
+        "hooks": 0
+      },
+      "tags": [
+        "specification",
+        "knowledge-graph",
+        "validation",
+        "mcp",
+        "local-first"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-16T00:00:00Z",
+      "updated_at": "2026-07-16T00:00:00Z"
+    },
     "ears": {
       "name": "EARS Requirements Syntax",
       "id": "ears",
@@ -1295,6 +1396,43 @@
       "created_at": "2026-07-08T00:00:00Z",
       "updated_at": "2026-07-08T00:00:00Z"
     },
+    "figma-starter": {
+      "name": "Figma Starter",
+      "id": "figma-starter",
+      "description": "Turns a Figma section's screens into per-screen spec.md files, an app-level user-stories.md, and a build-order.md, then hands off to /speckit.specify.",
+      "author": "WaveMaker",
+      "version": "1.0.0",
+      "download_url": "https://github.com/wavemaker/spec-kit-figma-starter/archive/refs/tags/v1.0.0.zip",
+      "repository": "https://github.com/wavemaker/spec-kit-figma-starter",
+      "homepage": "https://github.com/wavemaker/spec-kit-figma-starter",
+      "documentation": "https://github.com/wavemaker/spec-kit-figma-starter/blob/main/README.md",
+      "changelog": "https://github.com/wavemaker/spec-kit-figma-starter/blob/main/CHANGELOG.md",
+      "license": "MIT",
+      "category": "integration",
+      "effect": "read-write",
+      "requires": {
+        "speckit_version": ">=0.1.0",
+        "tools": [
+          { "name": "python3", "version": ">=3.8", "required": true }
+        ]
+      },
+      "provides": {
+        "commands": 1,
+        "hooks": 1
+      },
+      "tags": [
+        "figma",
+        "design",
+        "design-to-spec",
+        "ui",
+        "frontend"
+      ],
+      "verified": false,
+      "downloads": 0,
+      "stars": 0,
+      "created_at": "2026-07-15T00:00:00Z",
+      "updated_at": "2026-07-15T00:00:00Z"
+    },
     "fix-findings": {
       "name": "Fix Findings",
       "id": "fix-findings",
@@ -1438,13 +1576,14 @@
     "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).",
+      "description": "Deterministic quality enforcement for Spec Kit across agent hooks, git checks, and CI pipelines with one policy file and one verify entrypoint for identical results at every boundary.",
       "author": "schwichtgit",
-      "version": "0.1.0",
-      "download_url": "https://github.com/schwichtgit/spec-gates/releases/download/v0.1.0/gates-0.1.0.zip",
+      "version": "0.3.2",
+      "download_url": "https://github.com/schwichtgit/spec-gates/releases/download/v0.3.2/gates-0.3.2.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",
+      "changelog": "https://github.com/schwichtgit/spec-gates/releases",
       "license": "MIT",
       "category": "process",
       "effect": "read-write",
@@ -1457,7 +1596,7 @@
           },
           {
             "name": "git",
-            "required": true
+            "required": false
           },
           {
             "name": "node",
@@ -1470,8 +1609,8 @@
         ]
       },
       "provides": {
-        "commands": 5,
-        "hooks": 1
+        "commands": 8,
+        "hooks": 2
       },
       "tags": [
         "quality",
@@ -1484,7 +1623,7 @@
       "downloads": 0,
       "stars": 0,
       "created_at": "2026-07-09T00:00:00Z",
-      "updated_at": "2026-07-13T00:00:00Z"
+      "updated_at": "2026-07-15T00:00:00Z"
     },
     "github-issues": {
       "name": "GitHub Issues Integration 1",
@@ -2677,6 +2816,46 @@
       "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",

extensions/git/scripts/powershell/create-new-feature-branch.ps1

@@ -41,6 +41,16 @@ if ($Help) {
     exit 0
 }
 
+# -Number is [long], so PowerShell binds "-5" as -5 rather than rejecting it
+# the way the bash/Python twins do (`^[0-9]+$`). A negative value would format
+# via '{0:000}' to e.g. "-005" and produce a branch name starting with "-",
+# which git refuses (refs cannot begin with a dash). Reject it here, before the
+# description check, matching the bash twin's parse-time validation order.
+if ($Number -lt 0) {
+    Write-Error 'Error: --number must be a non-negative integer'
+    exit 1
+}
+
 if (-not $FeatureDescription -or $FeatureDescription.Count -eq 0) {
     Write-Error "Usage: ./create-new-feature-branch.ps1 [-Json] [-DryRun] [-AllowExistingBranch] [-ShortName <name>] [-Number N] [-Timestamp] <feature description>"
     exit 1

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())

integrations/catalog.json

@@ -1,6 +1,6 @@
 {
   "schema_version": "1.0",
-  "updated_at": "2026-06-23T00:00:00Z",
+  "updated_at": "2026-07-15T00:00:00Z",
   "catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/integrations/catalog.json",
   "integrations": {
     "claude": {
@@ -282,6 +282,15 @@
       "repository": "https://github.com/github/spec-kit",
       "tags": ["cli"]
     },
+    "grok": {
+      "id": "grok",
+      "name": "Grok Build",
+      "version": "1.0.0",
+      "description": "xAI Grok Build CLI skills-based integration",
+      "author": "spec-kit-core",
+      "repository": "https://github.com/github/spec-kit",
+      "tags": ["cli", "skills", "xai"]
+    },
     "hermes": {
       "id": "hermes",
       "name": "Hermes Agent",

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "specify-cli"
-version = "0.12.15.dev0"
+version = "0.12.18"
 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"

src/specify_cli/_invocation_style.py

@@ -12,7 +12,7 @@ from __future__ import annotations
 DOLLAR_SKILLS_AGENTS: frozenset[str] = frozenset({"codex", "zcode"})
 
 # Agents that always render /speckit-<name>, regardless of ai_skills.
-ALWAYS_SLASH_AGENTS: frozenset[str] = frozenset({"devin", "trae", "zed"})
+ALWAYS_SLASH_AGENTS: frozenset[str] = frozenset({"devin", "grok", "trae", "zed"})
 
 # Agents that render /speckit-<name> only when ai_skills is enabled.
 CONDITIONAL_SLASH_AGENTS: frozenset[str] = frozenset(

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:
@@ -476,8 +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:
@@ -605,6 +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
@@ -689,6 +701,7 @@ def register(app: typer.Typer) -> None:
         copilot_skill_mode = selected_ai == "copilot" and _is_skills_integration
         devin_skill_mode = selected_ai == "devin"
         zed_skill_mode = selected_ai == "zed" and _is_skills_integration
+        grok_skill_mode = selected_ai == "grok" and _is_skills_integration
         cline_skill_mode = selected_ai == "cline"
         native_skill_mode = (
             codex_skill_mode
@@ -701,6 +714,7 @@ def register(app: typer.Typer) -> None:
             or copilot_skill_mode
             or devin_skill_mode
             or zed_skill_mode
+            or grok_skill_mode
         )
 
         if codex_skill_mode:
@@ -733,6 +747,11 @@ def register(app: typer.Typer) -> None:
                 f"{step_num}. Start Zed in this project directory; spec-kit skills were installed to [cyan].agents/skills[/cyan]"
             )
             step_num += 1
+        if grok_skill_mode:
+            steps_lines.append(
+                f"{step_num}. Start Grok Build in this project directory; spec-kit skills were installed to [cyan].grok/skills[/cyan]"
+            )
+            step_num += 1
         usage_label = "skills" if native_skill_mode else "slash commands"
 
         from .._invocation_style import (

src/specify_cli/extensions/__init__.py

@@ -1004,6 +1004,7 @@ class ExtensionManager:
         from .. import load_init_options
         from ..agents import CommandRegistrar
         from ..integrations import get_integration
+        from ..integrations.base import IntegrationBase
 
         written: List[str] = []
         opts = load_init_options(self.project_root)
@@ -1015,6 +1016,30 @@ class ExtensionManager:
         registrar = CommandRegistrar()
         agent_config = registrar.AGENT_CONFIGS.get(selected_ai, {})
         integration = get_integration(selected_ai)
+        ai_skills_enabled = is_ai_skills_enabled(opts)
+
+        def _resolve_command_ref_tokens(body: str) -> str:
+            """Resolve explicit command-ref tokens with the active skill style."""
+
+            def _replacement(match: re.Match[str]) -> str:
+                command_name = "speckit." + match.group(1).lower().replace("_", ".")
+                if is_dollar_skills_agent(selected_ai, ai_skills_enabled):
+                    return "$" + command_name.replace("speckit.", "speckit-").replace(
+                        ".", "-"
+                    )
+                if is_slash_skills_agent(selected_ai, ai_skills_enabled):
+                    return "/" + command_name.replace("speckit.", "speckit-").replace(
+                        ".", "-"
+                    )
+                if integration is not None:
+                    return integration.build_command_invocation(command_name)
+                return IntegrationBase.resolve_command_refs(
+                    match.group(0), agent_config.get("invoke_separator", ".")
+                )
+
+            return re.sub(
+                r"__SPECKIT_COMMAND_([A-Z][A-Z0-9_]*)__", _replacement, body
+            )
 
         for cmd_info in manifest.commands:
             cmd_name = cmd_info["name"]
@@ -1086,6 +1111,7 @@ class ExtensionManager:
             body = registrar.resolve_skill_placeholders(
                 selected_ai, frontmatter, body, self.project_root, extension_id=manifest.id
             )
+            body = _resolve_command_ref_tokens(body)
 
             original_desc = frontmatter.get("description", "")
             description = original_desc or f"Extension command: {cmd_name}"

src/specify_cli/integrations/__init__.py

@@ -63,6 +63,7 @@ def _register_builtins() -> None:
     from .gemini import GeminiIntegration
     from .generic import GenericIntegration
     from .goose import GooseIntegration
+    from .grok import GrokIntegration
     from .hermes import HermesIntegration
     from .junie import JunieIntegration
     from .kilocode import KilocodeIntegration
@@ -99,6 +100,7 @@ def _register_builtins() -> None:
     _register(GeminiIntegration())
     _register(GenericIntegration())
     _register(GooseIntegration())
+    _register(GrokIntegration())
     _register(HermesIntegration())
     _register(JunieIntegration())
     _register(KilocodeIntegration())

src/specify_cli/integrations/_helpers.py

@@ -260,6 +260,7 @@ def _update_init_options_for_integration(
     project_root: Path,
     integration: Any,
     script_type: str | None = None,
+    parsed_options: dict[str, Any] | None = None,
 ) -> None:
     """Update init-options.json to reflect *integration* as the active one.
 
@@ -278,7 +279,17 @@ def _update_init_options_for_integration(
     opts["speckit_version"] = _get_speckit_version()
     if script_type:
         opts["script"] = script_type
-    if isinstance(integration, SkillsIntegration) or getattr(integration, "_skills_mode", False):
+    # Skills mode is either intrinsic (SkillsIntegration), set on the instance
+    # during setup() (_skills_mode), or requested via parsed options (e.g.
+    # Copilot's --skills, persisted as parsed_options["skills"]). The latter is
+    # the only signal available on the `use` path, where no setup() runs and a
+    # fresh integration instance has _skills_mode == False (issue #3550).
+    skills_mode = (
+        isinstance(integration, SkillsIntegration)
+        or getattr(integration, "_skills_mode", False)
+        or bool((parsed_options or {}).get("skills"))
+    )
+    if skills_mode:
         opts["ai_skills"] = True
     else:
         opts.pop("ai_skills", None)
@@ -334,7 +345,9 @@ def _set_default_integration(
             ) from exc
 
     _write_integration_json(project_root, key, installed_keys, settings)
-    _update_init_options_for_integration(project_root, integration, script_type=resolved_script)
+    _update_init_options_for_integration(
+        project_root, integration, script_type=resolved_script, parsed_options=parsed_options
+    )
 
 
 def _set_default_integration_or_exit(*args: Any, **kwargs: Any) -> None:

src/specify_cli/integrations/grok/__init__.py

@@ -0,0 +1,60 @@
+"""Grok Build integration — skills-based agent.
+
+Grok Build discovers project skills from ``.grok/skills/speckit-<name>/SKILL.md``
+(and also scans ``.agents/skills/``). Spec Kit installs into the native
+``.grok/skills`` tree so skills take highest local priority.
+"""
+
+from __future__ import annotations
+
+from ..base import SkillsIntegration
+
+
+class GrokIntegration(SkillsIntegration):
+    """Integration for xAI Grok Build CLI."""
+
+    key = "grok"
+    config = {
+        "name": "Grok Build",
+        "folder": ".grok/",
+        "commands_subdir": "skills",
+        "install_url": "https://docs.x.ai/build/overview",
+        "requires_cli": True,
+    }
+    registrar_config = {
+        "dir": ".grok/skills",
+        "format": "markdown",
+        "args": "$ARGUMENTS",
+        "extension": "/SKILL.md",
+    }
+    multi_install_safe = True
+
+    def build_exec_args(
+        self,
+        prompt: str,
+        *,
+        model: str | None = None,
+        output_json: bool = True,
+    ) -> list[str] | None:
+        """Build CLI arguments for non-interactive ``grok`` execution.
+
+        Mandatory headless flag:
+
+        * ``--always-approve`` — auto-approve tool executions so workflow
+          dispatch and ``dispatch_command()`` are not blocked at permission
+          gates (same role as Cursor's ``--force`` / Copilot's ``--yolo``).
+        """
+        if not self.config or not self.config.get("requires_cli"):
+            return None
+        args = [
+            self._resolve_executable(),
+            "-p",
+            prompt,
+            "--always-approve",
+        ]
+        self._apply_extra_args_env_var(args)
+        if model:
+            args.extend(["--model", model])
+        if output_json:
+            args.extend(["--output-format", "json"])
+        return args

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(
@@ -1629,8 +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,
@@ -1710,6 +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"
@@ -1717,6 +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):
@@ -1763,6 +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]]:

src/specify_cli/presets/_commands.py

@@ -484,6 +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]")
@@ -517,6 +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.")
@@ -551,6 +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/engine.py

@@ -508,6 +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]] = []
@@ -562,6 +563,7 @@ class RunState:
                 "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,
             }
@@ -654,6 +656,7 @@ class RunState:
         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", "")
 
@@ -810,6 +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()
 
@@ -820,6 +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
@@ -885,6 +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
@@ -1197,9 +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 []
@@ -1207,7 +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
 
 

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/if_then/__init__.py

@@ -22,10 +22,33 @@ class IfThenStep(StepBase):
         result = evaluate_condition(condition, context)
 
         if result:
+            branch_name = "then"
             branch = config.get("then", [])
         else:
+            branch_name = "else"
             branch = config.get("else", [])
 
+        # The engine does not auto-validate step config (see
+        # ``WorkflowEngine.load_workflow``), and it feeds ``next_steps`` straight
+        # into ``_execute_steps`` which iterates them as step mappings. A
+        # non-list branch (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 branch; fail this
+        # step loudly on an unvalidated run instead, mirroring the switch/fan-out
+        # steps. A missing ``else`` defaults to ``[]`` and stays valid.
+        if branch is None and branch_name == "else":
+            branch = []
+        elif not isinstance(branch, list):
+            return StepResult(
+                status=StepStatus.FAILED,
+                output={"condition_result": result},
+                error=(
+                    f"If step {config.get('id', '?')!r}: {branch_name!r} must be "
+                    f"a list of steps, got {type(branch).__name__}."
+                ),
+            )
+
         return StepResult(
             status=StepStatus.COMPLETED,
             output={"condition_result": result},

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

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import json
 import math
+import os
 import subprocess
 from typing import Any
 
@@ -40,6 +41,13 @@ class ShellStep(StepBase):
                 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
         # control commands; catalog-installed workflows should be reviewed
@@ -51,6 +59,7 @@ class ShellStep(StepBase):
                 capture_output=True,
                 text=True,
                 cwd=cwd,
+                env=env,
                 timeout=timeout,
             )
             output = {

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

@@ -42,6 +42,10 @@ class SwitchStep(StepBase):
             )
         for case_key, case_steps in cases.items():
             if str(case_key) == str_value:
+                if not isinstance(case_steps, list):
+                    return self._non_list_branch_failure(
+                        config, f"case {str(case_key)!r}", case_steps, value
+                    )
                 return StepResult(
                     status=StepStatus.COMPLETED,
                     output={"matched_case": str(case_key), "expression_value": value},
@@ -50,12 +54,41 @@ class SwitchStep(StepBase):
 
         # Default fallback
         default_steps = config.get("default", [])
+        if default_steps is None:
+            default_steps = []
+        elif not isinstance(default_steps, list):
+            return self._non_list_branch_failure(
+                config, "'default'", default_steps, value
+            )
         return StepResult(
             status=StepStatus.COMPLETED,
             output={"matched_case": "__default__", "expression_value": value},
             next_steps=default_steps,
         )
 
+    @staticmethod
+    def _non_list_branch_failure(
+        config: dict[str, Any], branch_label: str, branch: Any, value: Any
+    ) -> StepResult:
+        """Fail the step for a non-list branch instead of crashing the run.
+
+        ``validate`` rejects a non-list case/default branch, but the engine does
+        not auto-validate and feeds ``next_steps`` straight into
+        ``_execute_steps``, which iterates them as step mappings. A non-list
+        branch would be iterated element-wise (a dict yields its keys, a str its
+        characters) and crash the whole run with AttributeError on ``.get()``.
+        Fail this step loudly on an unvalidated run instead, mirroring the
+        non-mapping ``cases`` guard above.
+        """
+        return StepResult(
+            status=StepStatus.FAILED,
+            output={"matched_case": None, "expression_value": value},
+            error=(
+                f"Switch step {config.get('id', '?')!r}: {branch_label} must be "
+                f"a list of steps, got {type(branch).__name__}."
+            ),
+        )
+
     def validate(self, config: dict[str, Any]) -> list[str]:
         errors = super().validate(config)
         if "expression" not in config:

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,

tests/extensions/git/test_git_extension.py

@@ -653,6 +653,19 @@ class TestCreateFeatureBash:
         assert data["BRANCH_NAME"] == "000-zero"
         assert data["FEATURE_NUM"] == "000"
 
+    def test_negative_number_rejected(self, tmp_path: Path):
+        """A negative --number is rejected. Pins the canonical behavior the
+        PowerShell twin must mirror; a negative value would otherwise format to
+        e.g. '-005' and produce a branch name starting with '-', which git
+        refuses (refs cannot begin with a dash)."""
+        project = _setup_project(tmp_path)
+        result = _run_bash(
+            "create-new-feature-branch.sh", project,
+            "--json", "--dry-run", "--number", "-5", "--short-name", "neg", "Negative feature",
+        )
+        assert result.returncode != 0
+        assert "--number must be a non-negative integer" in result.stderr
+
 
 @pytest.mark.skipif(not HAS_PWSH, reason="pwsh not available")
 class TestCreateFeaturePowerShell:
@@ -974,6 +987,21 @@ class TestCreateFeaturePowerShell:
         assert data["BRANCH_NAME"] == "000-zero"
         assert data["FEATURE_NUM"] == "000"
 
+    def test_negative_number_rejected(self, tmp_path: Path):
+        """A negative -Number is rejected, matching the bash/Python twins'
+        '--number must be a non-negative integer'. Regression guard: -Number is
+        [long], so PowerShell binds '-5' as -5 rather than rejecting it the way
+        the twins' `^[0-9]+$` check does; the value would then format via
+        '{0:000}' to '-005' and yield a branch name starting with '-', which
+        git refuses (refs cannot begin with a dash)."""
+        project = _setup_project(tmp_path)
+        result = _run_pwsh(
+            "create-new-feature-branch.ps1", project,
+            "-Json", "-DryRun", "-Number", "-5", "-ShortName", "neg", "Negative feature",
+        )
+        assert result.returncode != 0
+        assert "--number must be a non-negative integer" in result.stderr
+
 
 # ── auto-commit.sh Tests ─────────────────────────────────────────────────────
 

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/integrations/test_cli.py

@@ -224,6 +224,66 @@ class TestInitIntegrationFlag:
         assert "Continuing without the optional preset" in normalized
         assert "Project ready" in normalized
 
+    def test_init_with_local_preset_seeds_manifest_constitution(
+        self, tmp_path, monkeypatch
+    ):
+        from typer.testing import CliRunner
+        from specify_cli import app
+        from specify_cli.presets import PresetManager
+
+        monkeypatch.setattr(
+            PresetManager,
+            "_seed_constitution_from_preset",
+            lambda *_args, **_kwargs: None,
+        )
+
+        preset_dir = tmp_path / "constitution-preset"
+        (preset_dir / "organization").mkdir(parents=True)
+        preset_content = "# Ratified Organization Constitution\n"
+        (preset_dir / "organization" / "ratified.md").write_text(preset_content)
+        (preset_dir / "preset.yml").write_text(
+            yaml.safe_dump({
+                "schema_version": "1.0",
+                "preset": {
+                    "id": "constitution-preset",
+                    "name": "Constitution Preset",
+                    "version": "1.0.0",
+                    "description": "Provides a ratified constitution",
+                },
+                "requires": {"speckit_version": ">=0.1.0"},
+                "provides": {
+                    "templates": [{
+                        "type": "template",
+                        "name": "constitution-template",
+                        "file": "organization/ratified.md",
+                        "strategy": "replace",
+                    }]
+                },
+            })
+        )
+        project = tmp_path / "init-with-preset"
+
+        result = CliRunner().invoke(
+            app,
+            [
+                "init",
+                str(project),
+                "--integration",
+                "copilot",
+                "--script",
+                "sh",
+                "--ignore-agent-tools",
+                "--preset",
+                str(preset_dir),
+            ],
+            catch_exceptions=False,
+        )
+
+        assert result.exit_code == 0, result.output
+        assert (
+            project / ".specify" / "memory" / "constitution.md"
+        ).read_text() == preset_content
+
     def test_integration_claude_here_preserves_preexisting_commands(self, tmp_path):
         from typer.testing import CliRunner
         from specify_cli import app
@@ -314,6 +374,18 @@ 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

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

@@ -431,6 +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_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",

tests/integrations/test_integration_generic.py

@@ -286,6 +286,7 @@ class TestGenericIntegration:
             ".specify/integration.json",
             ".specify/integrations/generic.manifest.json",
             ".specify/integrations/speckit.manifest.json",
+            ".specify/memory/.constitution-template.json",
             ".specify/memory/constitution.md",
             ".specify/scripts/bash/check-prerequisites.sh",
             ".specify/scripts/bash/common.sh",
@@ -342,6 +343,7 @@ class TestGenericIntegration:
             ".specify/integration.json",
             ".specify/integrations/generic.manifest.json",
             ".specify/integrations/speckit.manifest.json",
+            ".specify/memory/.constitution-template.json",
             ".specify/memory/constitution.md",
             ".specify/scripts/powershell/check-prerequisites.ps1",
             ".specify/scripts/powershell/common.ps1",

tests/integrations/test_integration_grok.py

@@ -0,0 +1,187 @@
+"""Tests for GrokIntegration."""
+
+import json
+
+import pytest
+
+from specify_cli.integrations import get_integration
+from specify_cli.integrations.manifest import IntegrationManifest
+
+from .test_integration_base_skills import SkillsIntegrationTests
+
+
+class TestGrokIntegration(SkillsIntegrationTests):
+    KEY = "grok"
+    FOLDER = ".grok/"
+    COMMANDS_SUBDIR = "skills"
+    REGISTRAR_DIR = ".grok/skills"
+
+    def test_options_include_skills_flag(self):
+        """Not applicable — Grok Build is always skills-based."""
+        pytest.skip("Grok Build is always skills-based and does not expose a --skills option")
+
+    def test_options_do_not_include_skills_flag(self):
+        i = get_integration(self.KEY)
+        assert i is not None
+        opts = i.options()
+        skills_opts = [o for o in opts if o.name == "--skills"]
+        assert len(skills_opts) == 0
+
+    def test_requires_cli_is_true(self):
+        i = get_integration(self.KEY)
+        assert i is not None
+        assert i.config["requires_cli"] is True
+        assert i.config["name"] == "Grok Build"
+        assert i.multi_install_safe is True
+
+
+class TestGrokInitFlow:
+    """--integration grok creates expected files."""
+
+    def test_integration_grok_creates_skills(self, tmp_path):
+        """--integration grok should create skills in .grok/skills."""
+        from typer.testing import CliRunner
+        from specify_cli import app
+
+        runner = CliRunner()
+        target = tmp_path / "test-proj"
+        result = runner.invoke(
+            app,
+            [
+                "init",
+                str(target),
+                "--integration",
+                "grok",
+                "--ignore-agent-tools",
+                "--script",
+                "sh",
+            ],
+            catch_exceptions=False,
+        )
+
+        assert result.exit_code == 0, f"init --integration grok failed: {result.output}"
+        assert (target / ".grok" / "skills" / "speckit-plan" / "SKILL.md").exists()
+        assert (target / ".grok" / "skills" / "speckit-specify" / "SKILL.md").exists()
+
+    def test_plan_skill_has_no_context_placeholder(self, tmp_path):
+        """Core skills must not carry a context-file placeholder."""
+        target = tmp_path / "test-proj"
+        target.mkdir()
+
+        integration = get_integration("grok")
+        manifest = IntegrationManifest("grok", target)
+        integration.setup(target, manifest, script_type="sh")
+
+        plan_skill = target / ".grok" / "skills" / "speckit-plan" / "SKILL.md"
+        content = plan_skill.read_text(encoding="utf-8")
+        assert "__CONTEXT_FILE__" not in content
+
+    def test_build_exec_args_uses_headless_prompt_flag(self):
+        integration = get_integration("grok")
+        args = integration.build_exec_args("hello", model="grok-build", output_json=True)
+        assert args is not None
+        assert args[0] == "grok" or args[0].endswith("/grok")
+        assert "-p" in args
+        assert "hello" in args
+        assert "--always-approve" in args
+        assert "--model" in args
+        assert "grok-build" in args
+        assert "--output-format" in args
+        assert "json" in args
+
+
+class TestGrokNextSteps:
+    """CLI output tests for Grok next-steps display."""
+
+    def test_init_next_steps_show_grok_skill_guidance(self, tmp_path):
+        """init --integration grok should guide users to .grok/skills and /speckit-*."""
+        from typer.testing import CliRunner
+        from specify_cli import app
+
+        runner = CliRunner()
+        target = tmp_path / "grok-next-steps"
+        result = runner.invoke(
+            app,
+            [
+                "init",
+                str(target),
+                "--integration",
+                "grok",
+                "--ignore-agent-tools",
+                "--script",
+                "sh",
+            ],
+            catch_exceptions=False,
+        )
+
+        assert result.exit_code == 0, f"init --integration grok failed: {result.output}"
+        assert "Start Grok Build" in result.output, (
+            f"Expected Grok start guidance in next steps but got:\n{result.output}"
+        )
+        assert ".grok/skills" in result.output, (
+            f"Expected .grok/skills install path in next steps but got:\n{result.output}"
+        )
+        assert "/speckit-plan" in result.output, (
+            f"Expected /speckit-plan in next steps but got:\n{result.output}"
+        )
+        assert "/speckit.plan" not in result.output, (
+            f"Should not show /speckit.plan for Grok skills mode:\n{result.output}"
+        )
+
+
+class TestGrokInitOptions:
+    """Init-options persistence for always-skills Grok."""
+
+    def test_init_persists_ai_skills_for_grok(self, tmp_path, monkeypatch):
+        """specify init --integration grok must persist ai_skills: true,
+        so HookExecutor renders slash-skill invocations without manual
+        init-options manipulation.
+        """
+        from typer.testing import CliRunner
+
+        from specify_cli import app
+        from specify_cli.extensions import HookExecutor
+
+        project = tmp_path / "grok-init-test"
+        project.mkdir()
+        monkeypatch.chdir(project)
+        runner = CliRunner()
+        result = runner.invoke(
+            app,
+            [
+                "init",
+                "--here",
+                "--integration",
+                "grok",
+                "--script",
+                "sh",
+                "--ignore-agent-tools",
+            ],
+            catch_exceptions=False,
+        )
+
+        assert result.exit_code == 0, f"init failed: {result.output}"
+
+        opts_path = project / ".specify" / "init-options.json"
+        assert opts_path.exists()
+        opts = json.loads(opts_path.read_text(encoding="utf-8"))
+        assert opts.get("ai") == "grok"
+        assert opts.get("ai_skills") is True, (
+            f"init must persist ai_skills=true for Grok, got: {opts.get('ai_skills')}"
+        )
+
+        hook_executor = HookExecutor(project)
+        message = hook_executor.format_hook_message(
+            "before_plan",
+            [
+                {
+                    "extension": "test-ext",
+                    "command": "speckit.plan",
+                    "optional": False,
+                }
+            ],
+        )
+        assert "Executing: `/speckit-plan`" in message, (
+            "Hook rendering must produce /speckit-plan for Grok without hint injection"
+        )
+        assert "EXECUTE_COMMAND_INVOCATION: /speckit-plan" in message

tests/integrations/test_integration_subcommand.py

@@ -1566,6 +1566,43 @@ class TestIntegrationUse:
         assert opts["integration"] == "codex"
         assert opts["ai"] == "codex"
 
+    def test_use_preserves_copilot_skills_mode(self, tmp_path):
+        """`use` on a skills-mode Copilot keeps ``ai_skills`` (issue #3550).
+
+        Re-selecting the same skills-mode Copilot must not drop ``ai_skills``
+        from init-options.json nor regenerate extension commands in the legacy
+        ``.agent.md``/``.prompt.md`` layout.
+        """
+        project = _init_project(tmp_path, "copilot", integration_options="--skills")
+
+        opts = json.loads((project / ".specify" / "init-options.json").read_text(encoding="utf-8"))
+        assert opts.get("ai_skills") is True, "precondition: init recorded skills mode"
+
+        result = _run_in_project(project, ["extension", "add", "git"])
+        assert result.exit_code == 0, f"extension add failed: {result.output}"
+
+        # Simulate a fresh process: `use` in real life runs in its own process
+        # where the registry's Copilot instance has _skills_mode == False (it is
+        # only set during setup()). In-process test invocations otherwise reuse
+        # the singleton left in skills mode by init, masking the bug (#3550).
+        from specify_cli.integrations import get_integration
+
+        get_integration("copilot")._skills_mode = False
+
+        result = _run_in_project(project, ["integration", "use", "copilot"])
+        assert result.exit_code == 0, result.output
+
+        opts = json.loads((project / ".specify" / "init-options.json").read_text(encoding="utf-8"))
+        assert opts.get("ai_skills") is True, "ai_skills must survive `use copilot`"
+
+        # No legacy command-layout files should be regenerated for the
+        # skills-mode agent.
+        assert not (project / ".github" / "agents" / "speckit.git.feature.agent.md").exists()
+        assert not (project / ".github" / "prompts" / "speckit.git.feature.prompt.md").exists()
+        assert (
+            project / ".github" / "skills" / "speckit-git-feature" / "SKILL.md"
+        ).exists()
+
     def test_use_requires_installed_integration(self, tmp_path):
         project = _init_project(tmp_path, "claude")
         old_cwd = os.getcwd()

tests/integrations/test_integration_zed.py

@@ -141,6 +141,8 @@ class TestSlashSkillsSets:
             # ALWAYS_SLASH_AGENTS — unconditional on ai_skills
             ("devin", True, "/speckit-plan"),
             ("devin", False, "/speckit-plan"),
+            ("grok", True, "/speckit-plan"),
+            ("grok", False, "/speckit-plan"),
             ("trae", True, "/speckit-plan"),
             ("trae", False, "/speckit-plan"),
             ("zed", True, "/speckit-plan"),

tests/test_agent_config_consistency.py

@@ -25,6 +25,7 @@ ISSUE_TEMPLATE_AGENT_KEYS = [
     "gemini",
     "copilot",
     "goose",
+    "grok",
     "hermes",
     "bob",
     "junie",

tests/test_extension_skills.py

@@ -970,6 +970,113 @@ class TestExtensionSkillRegistration:
         assert "Read agents/control" not in content
         assert "and knowledge-base/" not in content
 
+    @pytest.mark.parametrize(
+        ("ai", "expected_invocation"),
+        [
+            ("claude", "/speckit-plan"),
+            ("copilot", "/speckit-plan"),
+            ("codex", "$speckit-plan"),
+            ("kimi", "/skill:speckit-plan"),
+            ("zcode", "$speckit-plan"),
+        ],
+    )
+    def test_skill_registration_resolves_command_ref_tokens(
+        self, project_dir, temp_dir, ai, expected_invocation
+    ):
+        """Auto-registered skills should resolve explicit command ref tokens."""
+        _create_init_options(project_dir, ai=ai, ai_skills=True)
+        skills_dir = _create_skills_dir(project_dir, ai=ai)
+
+        ext_dir = temp_dir / "command-ref-ext"
+        ext_dir.mkdir()
+        manifest_data = {
+            "schema_version": "1.0",
+            "extension": {
+                "id": "command-ref-ext",
+                "name": "Command Ref Extension",
+                "version": "1.0.0",
+                "description": "Test",
+            },
+            "requires": {"speckit_version": ">=0.1.0"},
+            "provides": {
+                "commands": [
+                    {
+                        "name": "speckit.command-ref-ext.run",
+                        "file": "commands/run.md",
+                        "description": "Run command",
+                    }
+                ]
+            },
+        }
+        with open(ext_dir / "extension.yml", "w") as f:
+            yaml.safe_dump(manifest_data, f)
+
+        (ext_dir / "commands").mkdir()
+        (ext_dir / "commands" / "run.md").write_text(
+            "---\n"
+            "description: Run command\n"
+            "---\n\n"
+            "Use __SPECKIT_COMMAND_PLAN__ before proceeding.\n"
+        )
+
+        manager = ExtensionManager(project_dir)
+        manager.install_from_directory(ext_dir, "0.1.0", register_commands=False)
+
+        content = (skills_dir / "speckit-command-ref-ext-run" / "SKILL.md").read_text()
+        assert "__SPECKIT_COMMAND_PLAN__" not in content
+        assert expected_invocation in content
+
+    def test_skill_registration_does_not_rewrite_literal_speckit_text(
+        self, project_dir, temp_dir
+    ):
+        """Auto-registered skills should leave literal speckit text untouched."""
+        _create_init_options(project_dir, ai="codex", ai_skills=True)
+        skills_dir = _create_skills_dir(project_dir, ai="codex")
+
+        ext_dir = temp_dir / "literal-ref-ext"
+        ext_dir.mkdir()
+        manifest_data = {
+            "schema_version": "1.0",
+            "extension": {
+                "id": "literal-ref-ext",
+                "name": "Literal Ref Extension",
+                "version": "1.0.0",
+                "description": "Test",
+            },
+            "requires": {"speckit_version": ">=0.1.0"},
+            "provides": {
+                "commands": [
+                    {
+                        "name": "speckit.literal-ref-ext.run",
+                        "file": "commands/run.md",
+                        "description": "Run command",
+                    }
+                ]
+            },
+        }
+        with open(ext_dir / "extension.yml", "w") as f:
+            yaml.safe_dump(manifest_data, f)
+
+        (ext_dir / "commands").mkdir()
+        (ext_dir / "commands" / "run.md").write_text(
+            "---\n"
+            "description: Run command\n"
+            "---\n\n"
+            "Literal slash form: /speckit.foo.bar\n"
+            "Literal skill form: /speckit-plan\n"
+            "Literal bare form: speckit.foo.bar\n"
+        )
+
+        manager = ExtensionManager(project_dir)
+        manager.install_from_directory(ext_dir, "0.1.0", register_commands=False)
+
+        content = (skills_dir / "speckit-literal-ref-ext-run" / "SKILL.md").read_text()
+        assert "/speckit.foo.bar" in content
+        assert "/speckit-plan" in content
+        assert "speckit.foo.bar" in content
+        assert "/speckit-foo-bar" not in content
+        assert "$speckit-plan" not in content
+
     def test_missing_command_file_skipped(self, skills_project, temp_dir):
         """Commands with missing source files should be skipped gracefully."""
         project_dir, skills_dir = skills_project

tests/test_presets.py

@@ -2777,6 +2777,40 @@ def install_self_test_preset(manager: PresetManager, speckit_version: str = "0.1
         return manager.install_from_directory(SELF_TEST_PRESET_DIR, speckit_version)
 
 
+def _make_convention_constitution_preset(temp_dir: Path) -> Path:
+    """Create a preset whose constitution is found by convention, not its manifest."""
+    preset_dir = temp_dir / "convention-constitution"
+    (preset_dir / "templates").mkdir(parents=True)
+    (preset_dir / "templates" / "constitution-template.md").write_text(
+        "# Convention Constitution\n"
+    )
+    (preset_dir / "templates" / "spec-template.md").write_text("# Spec\n")
+    (preset_dir / "preset.yml").write_text(
+        yaml.dump(
+            {
+                "schema_version": "1.0",
+                "preset": {
+                    "id": "convention-constitution",
+                    "name": "Convention Constitution",
+                    "version": "1.0.0",
+                    "description": "Convention-based constitution for testing",
+                },
+                "requires": {"speckit_version": ">=0.1.0"},
+                "provides": {
+                    "templates": [
+                        {
+                            "type": "template",
+                            "name": "spec-template",
+                            "file": "templates/spec-template.md",
+                        }
+                    ]
+                },
+            }
+        )
+    )
+    return preset_dir
+
+
 class TestSelfTestPreset:
     """Tests using the self-test preset that ships with the repo.
 
@@ -2884,6 +2918,24 @@ class TestSelfTestPreset:
             assert result is not None
             assert result["source"] == "core"
 
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        assert memory.read_text() == "# Core constitution-template\n"
+
+    def test_self_test_removal_preserves_edited_constitution(self, project_dir):
+        """Removing a preset does not overwrite an edited generated constitution."""
+        templates_dir = project_dir / ".specify" / "templates"
+        (templates_dir / "constitution-template.md").write_text("# Core Constitution\n")
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        edited = memory.read_text() + "\n## Authored amendment\n"
+        memory.write_text(edited)
+
+        manager.remove("self-test")
+
+        assert memory.read_text() == edited
+
     def test_self_test_not_in_catalog(self):
         """Verify the self-test preset is NOT in the catalog (it's local-only)."""
         catalog_path = Path(__file__).parent.parent / "presets" / "catalog.json"
@@ -2958,6 +3010,432 @@ class TestSelfTestPreset:
         metadata = manager.registry.get("self-test")
         assert metadata["registered_commands"] == {}
 
+    def test_self_test_seeds_constitution_when_memory_absent(self, project_dir):
+        """Installing a preset seeds memory/constitution.md from its template."""
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        assert memory.exists(), "constitution.md was not seeded from the preset"
+        assert "preset:self-test" in memory.read_text(), (
+            "constitution.md was not seeded from the self-test preset template"
+        )
+
+    def test_self_test_reseeds_exact_core_constitution(self, project_dir):
+        """An unchanged core constitution is re-seeded from the preset template."""
+        resolver = PresetResolver(project_dir)
+        bundled_core = resolver._find_bundled_core(
+            "constitution-template", "template", ".md"
+        )
+        assert bundled_core is not None
+        core = bundled_core.read_bytes()
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        memory.parent.mkdir(parents=True, exist_ok=True)
+        memory.write_bytes(core)
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        content = memory.read_text()
+        assert "preset:self-test" in content, "placeholder constitution was not re-seeded"
+        assert "[PROJECT_NAME]" not in content
+
+    @pytest.mark.parametrize(
+        "provenance_content",
+        [
+            '{"sha256": "does-not-match", "source": "old-preset"}\n',
+            "{not valid json",
+        ],
+        ids=["hash-mismatch", "malformed"],
+    )
+    def test_self_test_preserves_core_content_with_existing_invalid_provenance(
+        self, project_dir, provenance_content
+    ):
+        """A present invalid sidecar disables legacy core-template migration."""
+        resolver = PresetResolver(project_dir)
+        bundled_core = resolver._find_bundled_core(
+            "constitution-template", "template", ".md"
+        )
+        assert bundled_core is not None
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        memory.parent.mkdir(parents=True, exist_ok=True)
+        memory.write_bytes(bundled_core.read_bytes())
+        (memory.parent / ".constitution-template.json").write_text(
+            provenance_content
+        )
+        original = memory.read_bytes()
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        assert memory.read_bytes() == original
+
+    def test_self_test_preserves_mutable_project_core_copy(self, project_dir):
+        """A project template copy does not establish generated provenance."""
+        authored = "# Acme Organization Constitution\n\nOrganization policy.\n"
+        project_template = (
+            project_dir / ".specify" / "templates" / "constitution-template.md"
+        )
+        project_template.write_text(authored)
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        memory.parent.mkdir(parents=True, exist_ok=True)
+        memory.write_text(authored)
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        assert memory.read_text() == authored
+        assert not (memory.parent / ".constitution-template.json").exists()
+
+    def test_core_prefixed_preset_does_not_establish_generated_provenance(
+        self, project_dir, temp_dir
+    ):
+        """A preset ID beginning with core is not an immutable core source."""
+        authored = "# Acme Organization Constitution\n\nOrganization policy.\n"
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        memory.parent.mkdir(parents=True, exist_ok=True)
+        memory.write_text(authored)
+
+        preset_dir = temp_dir / "core-company"
+        (preset_dir / "templates").mkdir(parents=True)
+        (preset_dir / "templates" / "constitution-template.md").write_text(authored)
+        (preset_dir / "preset.yml").write_text(
+            yaml.safe_dump(
+                {
+                    "schema_version": "1.0",
+                    "preset": {
+                        "id": "core-company",
+                        "name": "Core Company",
+                        "version": "1.0.0",
+                        "description": "Company constitution preset",
+                        "author": "Test Author",
+                        "repository": "https://github.com/test/core-company",
+                        "license": "MIT",
+                    },
+                    "requires": {"speckit_version": ">=0.1.0"},
+                    "provides": {
+                        "templates": [
+                            {
+                                "type": "template",
+                                "name": "constitution-template",
+                                "file": "templates/constitution-template.md",
+                                "description": "Company constitution",
+                                "replaces": "constitution-template",
+                            }
+                        ]
+                    },
+                }
+            )
+        )
+
+        PresetManager(project_dir).install_from_directory(preset_dir, "0.1.5")
+
+        assert memory.read_text() == authored
+        assert not (memory.parent / ".constitution-template.json").exists()
+
+    def test_self_test_preserves_authored_constitution_with_placeholder(
+        self, project_dir
+    ):
+        """A placeholder mention does not establish generated provenance."""
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        memory.parent.mkdir(parents=True, exist_ok=True)
+        authored = "# Acme Constitution\n\nGuidance for [PROJECT_NAME].\n"
+        memory.write_text(authored)
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        assert memory.read_text() == authored
+
+    def test_self_test_preserves_authored_constitution(self, project_dir):
+        """An authored (placeholder-free) constitution is never overwritten."""
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        memory.parent.mkdir(parents=True, exist_ok=True)
+        authored = "# Acme Constitution\n\n### I. Ship It\nAuthored by a human.\n"
+        memory.write_text(authored)
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        assert memory.read_text() == authored, "authored constitution was overwritten"
+
+    def test_self_test_override_resolves_constitution_template(self, project_dir):
+        """The preset override of constitution-template resolves to the preset file."""
+        templates_dir = project_dir / ".specify" / "templates"
+        (templates_dir / "constitution-template.md").write_text("# Core constitution\n")
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        resolver = PresetResolver(project_dir)
+        result = resolver.resolve("constitution-template", "template")
+        assert result is not None
+        assert "preset:self-test" in result.read_text()
+
+    def test_constitution_seed_composes_wrap_strategy(self, project_dir, temp_dir):
+        """Seeding memory composes wrap constitution-template layers."""
+        templates_dir = project_dir / ".specify" / "templates"
+        templates_dir.mkdir(parents=True, exist_ok=True)
+        (templates_dir / "constitution-template.md").write_text(
+            "# Core Constitution\n\n## Core Principle\n"
+        )
+
+        preset_dir = temp_dir / "constitution-wrap"
+        (preset_dir / "templates").mkdir(parents=True)
+        (preset_dir / "templates" / "constitution-template.md").write_text(
+            "# Wrapper Constitution\n\n{CORE_TEMPLATE}\n\n## Wrapper Footer\n"
+        )
+        (preset_dir / "preset.yml").write_text(
+            yaml.dump(
+                {
+                    "schema_version": "1.0",
+                    "preset": {
+                        "id": "constitution-wrap",
+                        "name": "Constitution Wrap",
+                        "version": "1.0.0",
+                        "description": "Wrap constitution template for testing",
+                    },
+                    "requires": {"speckit_version": ">=0.1.0"},
+                    "provides": {
+                        "templates": [
+                            {
+                                "type": "template",
+                                "name": "constitution-template",
+                                "file": "templates/constitution-template.md",
+                                "strategy": "wrap",
+                                "description": "Wrapped constitution template",
+                            }
+                        ]
+                    },
+                }
+            )
+        )
+
+        manager = PresetManager(project_dir)
+        manager.install_from_directory(preset_dir, "0.1.5")
+
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        content = memory.read_text()
+        assert "{CORE_TEMPLATE}" not in content
+        assert "# Wrapper Constitution" in content
+        assert "## Core Principle" in content
+
+    def test_constitution_follows_priority_when_winning_preset_removed(
+        self, project_dir, temp_dir
+    ):
+        """An unchanged generated constitution follows priority and fallback layers."""
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        preset_dir = temp_dir / "higher-priority"
+        (preset_dir / "templates").mkdir(parents=True)
+        (preset_dir / "templates" / "constitution-template.md").write_text(
+            "# Higher Priority Constitution\n"
+        )
+        (preset_dir / "preset.yml").write_text(
+            yaml.dump(
+                {
+                    "schema_version": "1.0",
+                    "preset": {
+                        "id": "higher-priority",
+                        "name": "Higher Priority",
+                        "version": "1.0.0",
+                        "description": "Higher-priority constitution",
+                    },
+                    "requires": {"speckit_version": ">=0.1.0"},
+                    "provides": {
+                        "templates": [
+                            {
+                                "type": "template",
+                                "name": "constitution-template",
+                                "file": "templates/constitution-template.md",
+                                "strategy": "replace",
+                                "description": "Higher-priority constitution",
+                            }
+                        ]
+                    },
+                }
+            )
+        )
+
+        manager.install_from_directory(preset_dir, "0.1.5", priority=1)
+
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        assert memory.read_text() == "# Higher Priority Constitution\n"
+
+        manager.remove("higher-priority")
+
+        assert "preset:self-test" in memory.read_text()
+
+    def test_convention_constitution_removal_restores_remaining_layer(
+        self, project_dir, temp_dir
+    ):
+        """Removing a convention layer rematerializes the remaining resolver layer."""
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+        manager.install_from_directory(
+            _make_convention_constitution_preset(temp_dir), "0.1.5", priority=1
+        )
+
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        assert memory.read_text() == "# Convention Constitution\n"
+
+        manager.remove("convention-constitution")
+
+        assert "preset:self-test" in memory.read_text()
+
+    def test_convention_constitution_removal_preserves_edited_content(
+        self, project_dir, temp_dir
+    ):
+        """Removing a convention layer does not overwrite edited generated content."""
+        from specify_cli.commands.init import ensure_constitution_from_template
+
+        templates_dir = project_dir / ".specify" / "templates"
+        (templates_dir / "constitution-template.md").write_text("# Core Constitution\n")
+        manager = PresetManager(project_dir)
+        manager.install_from_directory(
+            _make_convention_constitution_preset(temp_dir), "0.1.5"
+        )
+        ensure_constitution_from_template(project_dir)
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        edited = memory.read_text() + "\n## Authored amendment\n"
+        memory.write_text(edited)
+
+        manager.remove("convention-constitution")
+
+        assert memory.read_text() == edited
+
+    def test_custom_constitution_removal_recovers_with_invalid_manifest(
+        self, project_dir, temp_dir
+    ):
+        """Provenance triggers fallback when a custom-path manifest is invalid."""
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        preset_dir = temp_dir / "custom-constitution"
+        (preset_dir / "policy").mkdir(parents=True)
+        (preset_dir / "policy" / "charter.md").write_text("# Custom Constitution\n")
+        (preset_dir / "preset.yml").write_text(
+            yaml.dump(
+                {
+                    "schema_version": "1.0",
+                    "preset": {
+                        "id": "custom-constitution",
+                        "name": "Custom Constitution",
+                        "version": "1.0.0",
+                        "description": "Custom-path constitution for testing",
+                    },
+                    "requires": {"speckit_version": ">=0.1.0"},
+                    "provides": {
+                        "templates": [
+                            {
+                                "type": "template",
+                                "name": "constitution-template",
+                                "file": "policy/charter.md",
+                            }
+                        ]
+                    },
+                }
+            )
+        )
+        manager.install_from_directory(preset_dir, "0.1.5", priority=1)
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        assert memory.read_text() == "# Custom Constitution\n"
+
+        installed_manifest = (
+            project_dir
+            / ".specify"
+            / "presets"
+            / "custom-constitution"
+            / "preset.yml"
+        )
+        installed_manifest.write_text("invalid: [")
+
+        manager.remove("custom-constitution")
+
+        assert "preset:self-test" in memory.read_text()
+
+    def test_constitution_seed_rejects_symlinked_memory_directory(
+        self, project_dir, temp_dir
+    ):
+        """Preset installation cannot seed through a symlinked memory directory."""
+        outside = temp_dir / "outside"
+        outside.mkdir()
+        try:
+            (project_dir / ".specify" / "memory").symlink_to(
+                outside, target_is_directory=True
+            )
+        except OSError:
+            pytest.skip("symlinks are unavailable")
+
+        manager = PresetManager(project_dir)
+        with pytest.warns(UserWarning, match="symlinked"):
+            install_self_test_preset(manager)
+
+        assert manager.registry.is_installed("self-test")
+        assert not (outside / "constitution.md").exists()
+
+    def test_constitution_seed_rejects_dangling_destination_symlink(
+        self, project_dir, temp_dir
+    ):
+        """Preset installation cannot seed through a dangling destination symlink."""
+        memory = project_dir / ".specify" / "memory"
+        memory.mkdir(parents=True)
+        outside = temp_dir / "outside-constitution.md"
+        try:
+            (memory / "constitution.md").symlink_to(outside)
+        except OSError:
+            pytest.skip("symlinks are unavailable")
+
+        manager = PresetManager(project_dir)
+        with pytest.warns(UserWarning, match="symlinked"):
+            install_self_test_preset(manager)
+
+        assert manager.registry.is_installed("self-test")
+        assert not outside.exists()
+
+    def test_constitution_materialization_error_is_nonfatal(
+        self, project_dir, temp_dir
+    ):
+        """An invalid wrap warns without reporting an uninstalled preset."""
+        preset_dir = temp_dir / "invalid-wrap"
+        (preset_dir / "templates").mkdir(parents=True)
+        (preset_dir / "templates" / "constitution-template.md").write_text(
+            "# Missing core placeholder\n"
+        )
+        (preset_dir / "preset.yml").write_text(
+            yaml.dump(
+                {
+                    "schema_version": "1.0",
+                    "preset": {
+                        "id": "invalid-wrap",
+                        "name": "Invalid Wrap",
+                        "version": "1.0.0",
+                        "description": "Invalid wrapping constitution",
+                    },
+                    "requires": {"speckit_version": ">=0.1.0"},
+                    "provides": {
+                        "templates": [
+                            {
+                                "type": "template",
+                                "name": "constitution-template",
+                                "file": "templates/constitution-template.md",
+                                "strategy": "wrap",
+                                "description": "Invalid wrap",
+                            }
+                        ]
+                    },
+                }
+            )
+        )
+
+        manager = PresetManager(project_dir)
+        with pytest.warns(UserWarning, match="Failed to seed constitution"):
+            manifest = manager.install_from_directory(preset_dir, "0.1.5")
+
+        assert manifest.id == "invalid-wrap"
+        assert manager.registry.is_installed("invalid-wrap")
+
     def test_extension_command_skipped_when_extension_missing(self, project_dir, temp_dir):
         """Test that extension command overrides are skipped if the extension isn't installed."""
         claude_dir = project_dir / ".claude" / "skills"
@@ -4308,6 +4786,31 @@ class TestPresetSetPriority:
         manager2 = PresetManager(project_dir)
         assert manager2.registry.get("test-pack")["priority"] == 5
 
+    def test_set_priority_reconciles_generated_constitution(
+        self, project_dir, temp_dir
+    ):
+        """Changing priority rematerializes an unchanged generated constitution."""
+        from typer.testing import CliRunner
+        from unittest.mock import patch
+        from specify_cli import app
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+        manager.install_from_directory(
+            _make_convention_constitution_preset(temp_dir), "0.1.5", priority=20
+        )
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        assert "preset:self-test" in memory.read_text()
+
+        with patch.object(Path, "cwd", return_value=project_dir):
+            result = CliRunner().invoke(
+                app,
+                ["preset", "set-priority", "convention-constitution", "1"],
+            )
+
+        assert result.exit_code == 0, result.output
+        assert memory.read_text() == "# Convention Constitution\n"
+
     def test_set_priority_same_value_no_change(self, project_dir, pack_dir):
         """Test set-priority with same value shows already set message."""
         from typer.testing import CliRunner
@@ -4528,6 +5031,61 @@ class TestPresetEnableDisable:
         manager2 = PresetManager(project_dir)
         assert manager2.registry.get("test-pack")["enabled"] is True
 
+    def test_enable_disable_reconciles_generated_constitution(
+        self, project_dir, temp_dir
+    ):
+        """Enable and disable rematerialize the winning constitution layer."""
+        from typer.testing import CliRunner
+        from unittest.mock import patch
+        from specify_cli import app
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+        manager.install_from_directory(
+            _make_convention_constitution_preset(temp_dir), "0.1.5", priority=1
+        )
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        assert memory.read_text() == "# Convention Constitution\n"
+        runner = CliRunner()
+
+        with patch.object(Path, "cwd", return_value=project_dir):
+            disabled = runner.invoke(
+                app, ["preset", "disable", "convention-constitution"]
+            )
+
+        assert disabled.exit_code == 0, disabled.output
+        assert "preset:self-test" in memory.read_text()
+
+        with patch.object(Path, "cwd", return_value=project_dir):
+            enabled = runner.invoke(
+                app, ["preset", "enable", "convention-constitution"]
+            )
+
+        assert enabled.exit_code == 0, enabled.output
+        assert memory.read_text() == "# Convention Constitution\n"
+
+    def test_stack_changes_do_not_create_missing_constitution(
+        self, project_dir, pack_dir
+    ):
+        """Stack changes for non-providers do not seed a missing constitution."""
+        from typer.testing import CliRunner
+        from unittest.mock import patch
+        from specify_cli import app
+
+        PresetManager(project_dir).install_from_directory(pack_dir, "0.1.5")
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        runner = CliRunner()
+
+        for args in (
+            ["preset", "set-priority", "test-pack", "5"],
+            ["preset", "disable", "test-pack"],
+            ["preset", "enable", "test-pack"],
+        ):
+            with patch.object(Path, "cwd", return_value=project_dir):
+                result = runner.invoke(app, args)
+            assert result.exit_code == 0, result.output
+            assert not memory.exists()
+
     def test_disable_already_disabled(self, project_dir, pack_dir):
         """Test disable on already disabled preset shows warning."""
         from typer.testing import CliRunner
@@ -6678,3 +7236,130 @@ def test_preset_wrapper_resolves_ghes_asset_when_host_configured(tmp_path, monke
     )
     assert resolved == "https://ghes.example/api/v3/repos/o/r/releases/assets/9"
     assert captured == ["https://ghes.example/api/v3/repos/o/r/releases/tags/v2"]
+
+
+# ===== ensure_constitution_from_template resolver-awareness =====
+
+
+class TestEnsureConstitutionResolverAware:
+    """`ensure_constitution_from_template` must resolve through PresetResolver.
+
+    The constitution is the only template materialized to a live file rather
+    than resolved on demand. These tests pin the regression from issue #3272:
+    a preset-provided ``constitution-template`` must seed memory, while the
+    core template is used when no preset overrides it.
+    """
+
+    def _core_constitution(self, project_dir):
+        templates_dir = project_dir / ".specify" / "templates"
+        templates_dir.mkdir(parents=True, exist_ok=True)
+        (templates_dir / "constitution-template.md").write_text(
+            "# [PROJECT_NAME] Constitution\n\n### [PRINCIPLE_1_NAME]\n"
+        )
+
+    def _wrap_constitution_preset(self, temp_dir):
+        preset_dir = temp_dir / "ensure-wrap-preset"
+        (preset_dir / "templates").mkdir(parents=True)
+        (preset_dir / "templates" / "constitution-template.md").write_text(
+            "# Ensure Wrapper\n\n{CORE_TEMPLATE}\n\n## Tail\n"
+        )
+        (preset_dir / "preset.yml").write_text(
+            yaml.dump(
+                {
+                    "schema_version": "1.0",
+                    "preset": {
+                        "id": "ensure-wrap",
+                        "name": "Ensure Wrap",
+                        "version": "1.0.0",
+                        "description": "Wrap strategy for ensure() coverage",
+                    },
+                    "requires": {"speckit_version": ">=0.1.0"},
+                    "provides": {
+                        "templates": [
+                            {
+                                "type": "template",
+                                "name": "constitution-template",
+                                "file": "templates/constitution-template.md",
+                                "strategy": "wrap",
+                                "description": "Wrapped constitution",
+                            }
+                        ]
+                    },
+                }
+            )
+        )
+        return preset_dir
+
+    def test_seeds_from_core_when_no_preset(self, project_dir):
+        from specify_cli.commands.init import ensure_constitution_from_template
+
+        self._core_constitution(project_dir)
+        ensure_constitution_from_template(project_dir)
+
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        assert memory.exists()
+        assert "[PROJECT_NAME]" in memory.read_text()
+        assert (memory.parent / ".constitution-template.json").exists()
+
+    def test_seeds_from_preset_when_installed(self, project_dir):
+        from specify_cli.commands.init import ensure_constitution_from_template
+
+        self._core_constitution(project_dir)
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        # Remove the memory file seeded during install to test ensure() in
+        # isolation; it must re-seed from the preset, not the core template.
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        memory.unlink()
+
+        ensure_constitution_from_template(project_dir)
+
+        assert memory.exists()
+        content = memory.read_text()
+        assert "preset:self-test" in content
+        assert "[PROJECT_NAME]" not in content
+
+    def test_preserves_existing_memory(self, project_dir):
+        from specify_cli.commands.init import ensure_constitution_from_template
+
+        self._core_constitution(project_dir)
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        memory.parent.mkdir(parents=True, exist_ok=True)
+        authored = "# Acme Constitution\nAuthored.\n"
+        memory.write_text(authored)
+
+        ensure_constitution_from_template(project_dir)
+
+        assert memory.read_text() == authored
+
+    def test_preserves_edited_generated_memory(self, project_dir):
+        from specify_cli.commands.init import ensure_constitution_from_template
+
+        self._core_constitution(project_dir)
+        ensure_constitution_from_template(project_dir)
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        authored = memory.read_text() + "\nAuthored amendment.\n"
+        memory.write_text(authored)
+
+        manager = PresetManager(project_dir)
+        install_self_test_preset(manager)
+
+        assert memory.read_text() == authored
+
+    def test_composes_wrap_strategy_when_ensuring(self, project_dir, temp_dir):
+        from specify_cli.commands.init import ensure_constitution_from_template
+
+        self._core_constitution(project_dir)
+        manager = PresetManager(project_dir)
+        manager.install_from_directory(self._wrap_constitution_preset(temp_dir), "0.1.5")
+
+        # Ensure we validate ensure() behavior directly.
+        memory = project_dir / ".specify" / "memory" / "constitution.md"
+        memory.unlink()
+        ensure_constitution_from_template(project_dir)
+
+        content = memory.read_text()
+        assert "{CORE_TEMPLATE}" not in content
+        assert "# Ensure Wrapper" in content
+        assert "[PROJECT_NAME]" in content

tests/test_workflows.py

@@ -586,6 +586,51 @@ class TestExpressions:
         with pytest.raises(ValueError, match="unknown filter 'upper'"):
             evaluate_expression("{{ inputs.text | upper('x') }}", ctx)
 
+    def test_filter_map_non_string_attr_raises(self):
+        # A non-string attribute (authoring mistake like `map(5)`) must raise a
+        # ValueError naming the problem, not leak the cryptic AttributeError
+        # from attr.split() that would escape the evaluator and crash the run.
+        import pytest
+        from specify_cli.workflows.expressions import evaluate_expression
+        from specify_cli.workflows.base import StepContext
+
+        ctx = StepContext(inputs={"rows": [{"id": "a"}, {"id": "b"}]})
+        with pytest.raises(ValueError, match="map: expected a string attribute name"):
+            evaluate_expression("{{ inputs.rows | map(5) }}", ctx)
+
+    def test_filter_join_non_string_separator_raises(self):
+        # A non-string separator (authoring mistake like `join(5)`) must raise a
+        # ValueError, not leak the cryptic AttributeError from str.join.
+        import pytest
+        from specify_cli.workflows.expressions import evaluate_expression
+        from specify_cli.workflows.base import StepContext
+
+        ctx = StepContext(inputs={"tags": ["a", "b"]})
+        with pytest.raises(ValueError, match="join: expected a string separator"):
+            evaluate_expression("{{ inputs.tags | join(5) }}", ctx)
+
+    def test_filter_contains_non_string_arg_on_string_raises(self):
+        # For a string value, `contains` requires a string argument: `x in y` on
+        # a string needs a string left operand. A non-string argument must raise
+        # a ValueError, not leak the cryptic TypeError that would crash the run.
+        import pytest
+        from specify_cli.workflows.expressions import evaluate_expression
+        from specify_cli.workflows.base import StepContext
+
+        ctx = StepContext(inputs={"text": "hello"})
+        with pytest.raises(ValueError, match="contains: expected a string argument"):
+            evaluate_expression("{{ inputs.text | contains(5) }}", ctx)
+
+    def test_filter_contains_non_string_arg_on_list_ok(self):
+        # For a list value, membership of any element type is legitimate, so a
+        # non-string argument stays valid and is not rejected.
+        from specify_cli.workflows.expressions import evaluate_expression
+        from specify_cli.workflows.base import StepContext
+
+        ctx = StepContext(inputs={"nums": [1, 2, 5]})
+        assert evaluate_expression("{{ inputs.nums | contains(5) }}", ctx) is True
+        assert evaluate_expression("{{ inputs.nums | contains(9) }}", ctx) is False
+
     def test_registered_filters_unaffected(self):
         # Regression: all five registered filters keep working unchanged.
         from specify_cli.workflows.expressions import evaluate_expression
@@ -2067,6 +2112,69 @@ class TestIfThenStep:
         errors = step.validate({"id": "test", "then": []})
         assert any("missing 'condition'" in e for e in errors)
 
+    @pytest.mark.parametrize("bad_branch", [{"id": "x"}, "oops", 5])
+    def test_execute_non_list_then_fails_loudly(self, bad_branch):
+        """A non-list ``then`` must fail the step, not crash the run.
+
+        ``validate`` rejects a non-list ``then``, but the engine does not
+        auto-validate (see ``WorkflowEngine.load_workflow``) and feeds
+        ``next_steps`` straight into ``_execute_steps``, which iterates them as
+        step mappings. Before the guard, a non-list ``then`` (a single mapping
+        or scalar authoring mistake) was iterated element-wise and raised
+        AttributeError on ``.get()``, taking down the whole run. Mirrors the
+        switch/fan-out non-list handling.
+        """
+        from specify_cli.workflows.steps.if_then import IfThenStep
+        from specify_cli.workflows.base import StepContext, StepStatus
+
+        step = IfThenStep()
+        ctx = StepContext(inputs={})
+        result = step.execute(
+            {"id": "branch", "condition": "true", "then": bad_branch}, ctx
+        )
+        assert result.status == StepStatus.FAILED
+        assert "'then' must be a list of steps" in (result.error or "")
+        assert result.next_steps == []
+
+    @pytest.mark.parametrize("bad_branch", [{"id": "x"}, "oops", 5])
+    def test_execute_non_list_else_fails_loudly(self, bad_branch):
+        """A non-list ``else`` selected at runtime must fail the step, not crash.
+
+        Same asymmetry as ``then``: the ``else`` branch is only reached when the
+        condition is false, so a non-list ``else`` reaches ``next_steps`` and
+        would crash the engine's step iteration on an unvalidated run.
+        """
+        from specify_cli.workflows.steps.if_then import IfThenStep
+        from specify_cli.workflows.base import StepContext, StepStatus
+
+        step = IfThenStep()
+        ctx = StepContext(inputs={})
+        result = step.execute(
+            {"id": "branch", "condition": "false", "then": [], "else": bad_branch},
+            ctx,
+        )
+        assert result.status == StepStatus.FAILED
+        assert "'else' must be a list of steps" in (result.error or "")
+        assert result.next_steps == []
+
+    def test_execute_none_else_stays_empty(self):
+        """An explicit ``else: null`` selected at runtime stays an empty branch.
+
+        ``validate`` deliberately accepts ``else: None``; the execute guard must
+        normalize it to an empty branch (COMPLETED) rather than failing a
+        validator-approved workflow when the condition is false.
+        """
+        from specify_cli.workflows.steps.if_then import IfThenStep
+        from specify_cli.workflows.base import StepContext, StepStatus
+
+        step = IfThenStep()
+        ctx = StepContext(inputs={})
+        result = step.execute(
+            {"id": "branch", "condition": "false", "then": [], "else": None}, ctx
+        )
+        assert result.status == StepStatus.COMPLETED
+        assert result.next_steps == []
+
     @pytest.mark.parametrize("bad_else", [False, 0, "", {}, 42])
     def test_validate_rejects_non_list_else(self, bad_else):
         """A non-list 'else' must be rejected even when it is falsy.
@@ -2200,6 +2308,91 @@ class TestSwitchStep:
             # expression is still evaluated, so its value is surfaced for context.
             assert result.output["expression_value"] == "approve"
 
+    @pytest.mark.parametrize("bad_branch", [{"id": "x"}, "oops", 5])
+    def test_execute_non_list_matched_case_fails_loudly(self, bad_branch):
+        """A matched case with a non-list body must fail the step, not crash.
+
+        ``validate`` rejects a non-list case body, but the engine does not
+        auto-validate (see ``WorkflowEngine.load_workflow``) and feeds the
+        selected branch straight into ``_execute_steps``, which iterates it as
+        step mappings. A non-list body (a single mapping or scalar authoring
+        mistake) would be iterated element-wise and raise AttributeError on
+        ``.get()``, taking down the whole run. Mirrors the non-mapping
+        ``cases`` guard.
+        """
+        from specify_cli.workflows.steps.switch import SwitchStep
+        from specify_cli.workflows.base import StepContext, StepStatus
+
+        step = SwitchStep()
+        ctx = StepContext(steps={"review": {"output": {"choice": "approve"}}})
+        result = step.execute(
+            {
+                "id": "route",
+                "expression": "{{ steps.review.output.choice }}",
+                "cases": {"approve": bad_branch},
+            },
+            ctx,
+        )
+        assert result.status == StepStatus.FAILED
+        assert "case 'approve' must be a list of steps" in (result.error or "")
+        assert result.next_steps == []
+        # expression is still evaluated, so its value is surfaced for context.
+        assert result.output["expression_value"] == "approve"
+
+    @pytest.mark.parametrize("bad_branch", [{"id": "x"}, "oops", 5])
+    def test_execute_non_list_default_fails_loudly(self, bad_branch):
+        """A non-list ``default`` reached at runtime must fail, not crash.
+
+        Same asymmetry as the case body: ``default`` is only selected when no
+        case matches, so a non-list ``default`` reaches ``next_steps`` and would
+        crash the engine's step iteration on an unvalidated run.
+        """
+        from specify_cli.workflows.steps.switch import SwitchStep
+        from specify_cli.workflows.base import StepContext, StepStatus
+
+        step = SwitchStep()
+        ctx = StepContext(steps={"review": {"output": {"choice": "other"}}})
+        result = step.execute(
+            {
+                "id": "route",
+                "expression": "{{ steps.review.output.choice }}",
+                "cases": {"approve": [{"id": "plan", "command": "speckit.plan"}]},
+                "default": bad_branch,
+            },
+            ctx,
+        )
+        assert result.status == StepStatus.FAILED
+        assert "'default' must be a list of steps" in (result.error or "")
+        assert result.next_steps == []
+        # expression is still evaluated, so its value is surfaced for context.
+        assert result.output["expression_value"] == "other"
+
+    @pytest.mark.parametrize("ok_default", [None, [], [{"id": "x", "command": "/y"}]])
+    def test_execute_none_default_stays_empty(self, ok_default):
+        """An explicit ``default: null`` or a list default stays valid.
+
+        ``validate`` deliberately accepts ``default: None``; the execute guard
+        must normalize it to an empty branch (COMPLETED) rather than failing a
+        validator-approved workflow.
+        """
+        from specify_cli.workflows.steps.switch import SwitchStep
+        from specify_cli.workflows.base import StepContext, StepStatus
+
+        step = SwitchStep()
+        ctx = StepContext(steps={"review": {"output": {"choice": "other"}}})
+        result = step.execute(
+            {
+                "id": "route",
+                "expression": "{{ steps.review.output.choice }}",
+                "cases": {"approve": [{"id": "plan", "command": "speckit.plan"}]},
+                "default": ok_default,
+            },
+            ctx,
+        )
+        assert result.status == StepStatus.COMPLETED
+        assert result.output["matched_case"] == "__default__"
+        assert result.next_steps == (ok_default or [])
+
     def test_validate_missing_expression(self):
         from specify_cli.workflows.steps.switch import SwitchStep
 
@@ -2260,6 +2453,47 @@ class TestWhileStep:
         assert result.output["condition_result"] is False
         assert result.next_steps == []
 
+    @pytest.mark.parametrize("bad_steps", [{"id": "x"}, "oops", 5])
+    def test_execute_non_list_steps_fails_loudly(self, bad_steps):
+        """A non-list ``steps`` reached at runtime must fail the step, not crash.
+
+        ``validate`` rejects a non-list ``steps``, but the engine does not
+        auto-validate (see ``WorkflowEngine.load_workflow``) and feeds
+        ``next_steps`` straight into ``_execute_steps``, which iterates them as
+        step mappings. The while body only dispatches when the condition is
+        truthy, so a non-list ``steps`` reaches ``next_steps`` and would crash
+        the engine's step iteration on an unvalidated run. Mirrors the
+        if/switch/fan-out non-list handling.
+        """
+        from specify_cli.workflows.steps.while_loop import WhileStep
+        from specify_cli.workflows.base import StepContext, StepStatus
+
+        step = WhileStep()
+        ctx = StepContext(inputs={})
+        result = step.execute(
+            {"id": "retry", "condition": "true", "steps": bad_steps}, ctx
+        )
+        assert result.status == StepStatus.FAILED
+        assert "'steps' must be a list of steps" in (result.error or "")
+        assert result.next_steps == []
+
+    @pytest.mark.parametrize("bad_steps", [{"id": "x"}, "oops", 5])
+    def test_execute_non_list_steps_ok_when_condition_false(self, bad_steps):
+        """A false condition never dispatches the body, so a non-list ``steps``
+        stays benign — the step completes without touching ``next_steps``.
+        """
+        from specify_cli.workflows.steps.while_loop import WhileStep
+        from specify_cli.workflows.base import StepContext, StepStatus
+
+        step = WhileStep()
+        ctx = StepContext(inputs={})
+        result = step.execute(
+            {"id": "retry", "condition": "false", "steps": bad_steps}, ctx
+        )
+        assert result.status == StepStatus.COMPLETED
+        assert result.output["condition_result"] is False
+        assert result.next_steps == []
+
     def test_validate_missing_fields(self):
         from specify_cli.workflows.steps.while_loop import WhileStep
 
@@ -2350,6 +2584,30 @@ class TestDoWhileStep:
         assert result.next_steps == []
         assert result.status.value == "completed"
 
+    @pytest.mark.parametrize("bad_steps", [{"id": "x"}, "oops", 5])
+    def test_execute_non_list_steps_fails_loudly(self, bad_steps):
+        """A non-list ``steps`` must fail the step, not crash the run.
+
+        ``validate`` rejects a non-list ``steps``, but the engine does not
+        auto-validate (see ``WorkflowEngine.load_workflow``) and feeds
+        ``next_steps`` straight into ``_execute_steps``, which iterates them as
+        step mappings. The do-while body always dispatches on the first call
+        regardless of condition, so a non-list ``steps`` always reaches
+        ``next_steps`` and would crash the engine's step iteration on an
+        unvalidated run. Mirrors the if/switch/fan-out non-list handling.
+        """
+        from specify_cli.workflows.steps.do_while import DoWhileStep
+        from specify_cli.workflows.base import StepContext, StepStatus
+
+        step = DoWhileStep()
+        ctx = StepContext(inputs={})
+        result = step.execute(
+            {"id": "cycle", "condition": "false", "steps": bad_steps}, ctx
+        )
+        assert result.status == StepStatus.FAILED
+        assert "'steps' must be a list of steps" in (result.error or "")
+        assert result.next_steps == []
+
     def test_validate_missing_fields(self):
         from specify_cli.workflows.steps.do_while import DoWhileStep
 
@@ -2662,8 +2920,13 @@ class TestFanOutConcurrency:
         results, _ = self._run(tmp_path, list(range(n)), n, on_item)
         assert results == [{"seen": i} for i in range(n)]
 
-    @pytest.mark.parametrize("bad", [0, -1, None, "abc", 1.0])
+    @pytest.mark.parametrize(
+        "bad", [0, -1, None, "abc", 1.0, float("inf"), float("nan")]
+    )
     def test_invalid_max_concurrency_coerces_to_sequential(self, tmp_path, bad):
+        # float("inf") -> int() raises OverflowError (not TypeError/ValueError);
+        # it must fall back to sequential like any other uncoercible value, not
+        # crash the run.
         results, _ = self._run(tmp_path, list(range(4)), bad)
         assert results == [{"seen": i} for i in range(4)]
 
@@ -4446,6 +4709,286 @@ steps:
         assert state.step_results["stamp"]["output"]["stdout"].strip() == "explicit-456"
 
 
+# ===== context.workflow_dir Tests =====
+
+
+class TestContextWorkflowDir:
+    """Tests for `{{ context.workflow_dir }}` and `SPECKIT_WORKFLOW_DIR`."""
+
+    def test_context_workflow_dir_resolves(self):
+        """``{{ context.workflow_dir }}`` resolves to ``StepContext.workflow_dir``."""
+        from specify_cli.workflows.expressions import evaluate_expression
+        from specify_cli.workflows.base import StepContext
+
+        ctx = StepContext(workflow_dir="/home/user/my-workflow")
+        assert evaluate_expression("{{ context.workflow_dir }}", ctx) == "/home/user/my-workflow"
+
+    def test_context_workflow_dir_defaults_to_empty_when_unset(self):
+        """``{{ context.workflow_dir }}`` resolves to ``""`` when no source
+        path is available (string-loaded workflows, dry-run).
+        """
+        from specify_cli.workflows.expressions import evaluate_expression
+        from specify_cli.workflows.base import StepContext
+
+        ctx = StepContext()
+        assert evaluate_expression("{{ context.workflow_dir }}", ctx) == ""
+
+    def test_context_workflow_dir_string_interpolation(self):
+        """Workflow dir interpolates inside a larger template string."""
+        from specify_cli.workflows.expressions import evaluate_expression
+        from specify_cli.workflows.base import StepContext
+
+        ctx = StepContext(workflow_dir="/opt/workflows/setup")
+        result = evaluate_expression("cp {{ context.workflow_dir }}/config.yml .", ctx)
+        assert result == "cp /opt/workflows/setup/config.yml ."
+
+    def test_step_context_workflow_dir(self):
+        """StepContext accepts and stores workflow_dir."""
+        from specify_cli.workflows.base import StepContext
+
+        ctx = StepContext(workflow_dir="/some/path")
+        assert ctx.workflow_dir == "/some/path"
+
+        ctx_none = StepContext()
+        assert ctx_none.workflow_dir is None
+
+    def test_from_yaml_sets_workflow_dir(self, project_dir):
+        """Workflow loaded from a YAML file has workflow_dir set to the
+        file's parent directory.
+        """
+        from specify_cli.workflows.engine import WorkflowDefinition, WorkflowEngine
+
+        wf_dir = project_dir / "my-workflows"
+        wf_dir.mkdir()
+        wf_file = wf_dir / "setup.yml"
+        wf_file.write_text("""
+schema_version: "1.0"
+workflow:
+  id: "from-yaml"
+  name: "From YAML"
+  version: "1.0.0"
+steps:
+  - id: check-dir
+    type: shell
+    run: "echo DIR={{ context.workflow_dir }}"
+""")
+        definition = WorkflowDefinition.from_yaml(wf_file)
+        engine = WorkflowEngine(project_dir)
+        state = engine.execute(definition)
+
+        stdout = state.step_results["check-dir"]["output"]["stdout"]
+        assert stdout.strip() == f"DIR={wf_dir.resolve()}"
+
+    def test_from_string_has_empty_workflow_dir(self, project_dir):
+        """String-loaded workflows have empty workflow_dir."""
+        from specify_cli.workflows.engine import WorkflowDefinition, WorkflowEngine
+
+        definition = WorkflowDefinition.from_string("""
+schema_version: "1.0"
+workflow:
+  id: "from-string"
+  name: "From String"
+  version: "1.0.0"
+steps:
+  - id: check-dir
+    type: shell
+    run: "echo DIR={{ context.workflow_dir }}"
+""")
+        engine = WorkflowEngine(project_dir)
+        state = engine.execute(definition)
+
+        stdout = state.step_results["check-dir"]["output"]["stdout"]
+        assert stdout.strip() == "DIR="
+
+    def test_shell_step_receives_speckit_workflow_dir_env_var(self, project_dir):
+        """Shell steps receive SPECKIT_WORKFLOW_DIR in their environment."""
+        from specify_cli.workflows.engine import WorkflowDefinition, WorkflowEngine
+        import sys
+
+        wf_dir = project_dir / "wf"
+        wf_dir.mkdir()
+        wf_file = wf_dir / "workflow.yml"
+        python = sys.executable.replace("\\", "/")
+        wf_file.write_text(f"""
+schema_version: "1.0"
+workflow:
+  id: "env-var-test"
+  name: "Env Var Test"
+  version: "1.0.0"
+steps:
+  - id: print-env
+    type: shell
+    run: '"{python}" -c "import os; print(os.environ.get(''SPECKIT_WORKFLOW_DIR'', ''UNSET''))"'
+""")
+        definition = WorkflowDefinition.from_yaml(wf_file)
+        engine = WorkflowEngine(project_dir)
+        state = engine.execute(definition)
+
+        stdout = state.step_results["print-env"]["output"]["stdout"]
+        assert stdout.strip() == str(wf_dir.resolve())
+
+    def test_shell_step_no_env_var_when_workflow_dir_unset(self, project_dir, monkeypatch):
+        """Shell steps do not set SPECKIT_WORKFLOW_DIR for string-loaded workflows."""
+        from specify_cli.workflows.engine import WorkflowDefinition, WorkflowEngine
+        import sys
+
+        monkeypatch.delenv("SPECKIT_WORKFLOW_DIR", raising=False)
+
+        python = sys.executable.replace("\\", "/")
+        definition = WorkflowDefinition.from_string(f"""
+schema_version: "1.0"
+workflow:
+  id: "no-env-var"
+  name: "No Env Var"
+  version: "1.0.0"
+steps:
+  - id: check-env
+    type: shell
+    run: '"{python}" -c "import os; print(os.environ.get(''SPECKIT_WORKFLOW_DIR'', ''UNSET''))"'
+""")
+        engine = WorkflowEngine(project_dir)
+        state = engine.execute(definition)
+
+        stdout = state.step_results["check-env"]["output"]["stdout"]
+        assert stdout.strip() == "UNSET"
+
+    def test_resume_preserves_original_workflow_dir(self, project_dir):
+        """Resumed workflow uses the original source directory, not the
+        run-directory copy path.
+        """
+        from specify_cli.workflows.engine import WorkflowDefinition, WorkflowEngine
+        from specify_cli.workflows.base import RunStatus
+
+        wf_dir = project_dir / "original-source"
+        wf_dir.mkdir()
+        wf_file = wf_dir / "resumable.yml"
+        wf_file.write_text("""
+schema_version: "1.0"
+workflow:
+  id: "resumable"
+  name: "Resumable"
+  version: "1.0.0"
+steps:
+  - id: gate-step
+    type: gate
+    message: "Approve?"
+  - id: after-gate
+    type: shell
+    run: "echo DIR={{ context.workflow_dir }}"
+""")
+        definition = WorkflowDefinition.from_yaml(wf_file)
+        engine = WorkflowEngine(project_dir)
+
+        # Execute -- gate pauses the workflow
+        state = engine.execute(definition)
+        assert state.status == RunStatus.PAUSED
+        assert state.workflow_dir == str(wf_dir.resolve())
+
+        # Simulate gate approval by patching the gate step
+        from unittest.mock import patch
+        from specify_cli.workflows.base import StepResult
+
+        with patch(
+            "specify_cli.workflows.steps.gate.GateStep.execute",
+            return_value=StepResult(output={"approved": True}),
+        ):
+            state = engine.resume(state.run_id)
+
+        assert state.status == RunStatus.COMPLETED
+        stdout = state.step_results["after-gate"]["output"]["stdout"]
+        assert stdout.strip() == f"DIR={wf_dir.resolve()}"
+
+    def test_workflow_dir_persisted_in_state(self, project_dir):
+        """workflow_dir is persisted in state.json and survives load/save."""
+        from specify_cli.workflows.engine import WorkflowDefinition, WorkflowEngine, RunState
+
+        wf_dir = project_dir / "persist-test"
+        wf_dir.mkdir()
+        wf_file = wf_dir / "workflow.yml"
+        wf_file.write_text("""
+schema_version: "1.0"
+workflow:
+  id: "persist-wfdir"
+  name: "Persist WfDir"
+  version: "1.0.0"
+steps:
+  - id: noop
+    type: shell
+    run: "echo ok"
+""")
+        definition = WorkflowDefinition.from_yaml(wf_file)
+        engine = WorkflowEngine(project_dir)
+        state = engine.execute(definition)
+
+        # Reload state from disk and verify workflow_dir survived
+        loaded = RunState.load(state.run_id, project_dir)
+        assert loaded.workflow_dir == str(wf_dir.resolve())
+
+    def test_installed_workflow_has_workflow_dir(self, project_dir):
+        """Installed-by-ID workflows get workflow_dir pointing to the
+        installation directory (.specify/workflows/<id>/).
+        """
+        from specify_cli.workflows.engine import WorkflowEngine
+        from specify_cli.workflows.base import RunStatus
+
+        wf_id = "installed-wfdir"
+        install_dir = project_dir / ".specify" / "workflows" / wf_id
+        install_dir.mkdir(parents=True)
+        (install_dir / "workflow.yml").write_text("""
+schema_version: "1.0"
+workflow:
+  id: "installed-wfdir"
+  name: "Installed WfDir"
+  version: "1.0.0"
+steps:
+  - id: check-dir
+    type: shell
+    run: "echo DIR={{ context.workflow_dir }}"
+""")
+        engine = WorkflowEngine(project_dir)
+        definition = engine.load_workflow(wf_id)
+        state = engine.execute(definition)
+
+        assert state.status == RunStatus.COMPLETED
+        stdout = state.step_results["check-dir"]["output"]["stdout"]
+        assert stdout.strip() == f"DIR={install_dir.resolve()}"
+
+    def test_workflow_dir_is_resolved_to_absolute(self, project_dir):
+        """workflow_dir is resolved to an absolute path even when the
+        source path is relative.
+        """
+        from specify_cli.workflows.engine import WorkflowDefinition, WorkflowEngine
+        import os
+
+        wf_dir = project_dir / "rel-test"
+        wf_dir.mkdir()
+        wf_file = wf_dir / "workflow.yml"
+        wf_file.write_text("""
+schema_version: "1.0"
+workflow:
+  id: "rel-path"
+  name: "Relative Path"
+  version: "1.0.0"
+steps:
+  - id: check
+    type: shell
+    run: "echo ok"
+""")
+        # Load via a relative path
+        saved_cwd = os.getcwd()
+        try:
+            os.chdir(project_dir)
+            rel_path = Path("rel-test/workflow.yml")
+            definition = WorkflowDefinition.from_yaml(rel_path)
+            engine = WorkflowEngine(project_dir)
+            state = engine.execute(definition)
+        finally:
+            os.chdir(saved_cwd)
+
+        assert Path(state.workflow_dir).is_absolute()
+        assert state.workflow_dir == str(wf_dir.resolve())
+
+
 # ===== continue_on_error Tests =====
 #
 # Locks the contract documented in workflows/README.md "Error Handling"

workflows/README.md

@@ -348,6 +348,7 @@ current run:
 | Variable | Description |
 |----------|-------------|
 | `context.run_id` | The current workflow run id (the same value Spec Kit prints as `Run ID:` at the end of `workflow run`). Auto-generated runs are 8-character hex from `uuid4`; operator-supplied ids may be any alphanumeric string with hyphens or underscores. Empty string outside a run context. |
+| `context.workflow_dir` | The resolved absolute path to the directory containing the workflow source file. For file-loaded workflows this is the parent directory of the YAML file; for installed-by-ID workflows it is the absolute path to the installation directory (e.g. `<project>/.specify/workflows/<id>/`); for string-loaded workflows it is an empty string. On resume the original source directory is preserved from the first execution. |
 
 ```yaml
 # Stamp telemetry events with the run id for cross-system join.
@@ -365,6 +366,11 @@ current run:
   command: speckit.specify
   input:
     args: "{{ context.run_id }}"
+
+# Reference a sibling file shipped alongside the workflow definition.
+- id: apply-config
+  type: shell
+  run: 'cp "{{ context.workflow_dir }}/defaults.yml" ./config.yml'
 ```
 
 ## Input Types
@@ -445,6 +451,7 @@ specify workflow catalog remove <index>
 | Variable | Description |
 |----------|-------------|
 | `SPECKIT_WORKFLOW_CATALOG_URL` | Override the catalog URL (replaces all defaults) |
+| `SPECKIT_WORKFLOW_DIR` | Set automatically for shell steps; contains the resolved absolute path to the workflow source directory (same value as `{{ context.workflow_dir }}`). Not set when the workflow has no source path (string-loaded workflows). |
 
 ## Configuration Files