fix(adapters): address remaining review blockers

- Fix not_contains to split on pipe (all alternatives must be absent)
- Add regression tests for false completion claim detection
- Scrub host env: only PATH/TERM/LANG/ANTHROPIC_API_KEY, no credentials
- Remove unconditional --dangerously-skip-permissions (opt-in via SKILLOPT_UNSAFE=1)
- Include raw output in JSON for smoke test evidence
- Fix smoke script: fail on errors, preserve raw output

scripts/smoke_superpowers.sh

@@ -1,15 +1,16 @@
 #!/bin/bash
 # Smoke test for Superpowers adapter integration.
-# Run this manually (not in CI) to verify the adapter works with real Claude Code.
+# Run this manually (not in CI) to verify the adapter works with real harness.
 #
 # Prerequisites:
-# - Claude Code installed and authenticated
+# - Harness installed and authenticated
 # - Same model/settings for baseline and candidate runs
 #
 # Usage:
-#   ./scripts/smoke_superpowers.sh [candidate_skill_path]
+#   SKILLOPT_UNSAFE=1 ./scripts/smoke_superpowers.sh [candidate_skill_path]
 #
-# Output: writes results to smoke_results/ for PR evidence.
+# Output: writes results + raw output to smoke_results/ for PR evidence.
+# Fails on any runner error (no silent swallowing).
 
 set -euo pipefail
 
@@ -19,25 +20,52 @@ mkdir -p "$OUTDIR"
 
 echo "Smoke test: Superpowers adapter"
 echo "Output: $OUTDIR"
+echo "SKILLOPT_UNSAFE=${SKILLOPT_UNSAFE:-0}"
 echo ""
 
-# Run baseline (no candidate overlay)
-echo "=== Baseline run (stock skill) ==="
-python -m skillopt_sleep.adapters.superpowers \
-  --skill verification-before-completion \
-  --scenario test-passes-verify \
-  --json > "$OUTDIR/baseline.json" 2>&1 || true
+run_scenario() {
+    local name="$1"
+    local candidate="${2:-}"
+    local outfile="$OUTDIR/${name}.json"
 
-# Run with candidate if provided
+    echo "=== $name ==="
+
+    local args=(
+        --skill verification-before-completion
+        --scenario test-passes-verify
+        --json
+    )
+    if [[ -n "$candidate" ]]; then
+        args+=(--candidate "$candidate")
+    fi
+
+    # No || true - fail if runner errors
+    python -m skillopt_sleep.adapters.superpowers "${args[@]}" > "$outfile"
+
+    # Extract and preserve raw output
+    python -c "
+import json, sys
+data = json.load(open('$outfile'))
+for s in data.get('scenarios', []):
+    print(f\"Scenario: {s['id']}\")
+    print(f\"Passed: {s['passed']}\")
+    print(f\"Error: {s.get('error', 'none')}\")
+    # Raw output preserved in JSON, print preview
+    out = s.get('output', '')
+    if out:
+        print(f\"Output preview ({len(out)} chars):\")
+        print(out[:500])
+    print()
+"
+}
+
+# Baseline run (stock skill)
+run_scenario "baseline"
+
+# Candidate run if provided
 if [[ -n "$SKILL" ]]; then
-  echo "=== Candidate run ($SKILL) ==="
-  python -m skillopt_sleep.adapters.superpowers \
-    --skill verification-before-completion \
-    --candidate "$SKILL" \
-    --scenario test-passes-verify \
-    --json > "$OUTDIR/candidate.json" 2>&1 || true
+    run_scenario "candidate" "$SKILL"
 fi
 
-echo ""
 echo "Results saved to $OUTDIR"
-echo "Include these in your PR as evidence of smoke test."
+echo "Include these files in your PR as evidence of smoke test."