v1.41.1: MCP-tool hook audit conclusion (#218) - #250
Merged
Conversation
ROADMAP #218: CC 2.1.118 added type:'mcp_tool' for hooks. Audited all 5 wizard hooks (sdlc-prompt-check, instructions-loaded-check, tdd-pretool- check, model-effort-check, precompact-seam-check). Conclusion: all stay bash. Per-hook rationale documented under "Known CC Gotchas → MCP-tool hooks audit" so future PRs don't redo the work. Decision criteria: portability (Codex/OpenCode siblings), fail-closed gating (bash exit 2 fails closed; MCP server errors fail open), local-only state (cache files, handoff.json don't surface across tools). Codex round 1: 5/10 NOT CERTIFIED. 4 P1 findings — all real: - AUDIT-001: portability claim cited wrong Codex path (~/.codex/agents/... didn't exist; actual is ~/codex-sdlc-wizard). OpenCode sibling marked 'planned' per ROADMAP #91, not shipped. Fixed. - AUDIT-002: oversimplified "MCP can't gate" claim. CC docs confirm mcp_tool hooks CAN return decision:"block". Real concern: MCP server errors are non-blocking by design — that flips fail-closed (bash) to fail-open (MCP). Rewrote criterion. - AUDIT-003: per-hook rationale was filler ("MCP overkill", "Portability rules"). Each bullet now applies ≥1 criterion explicitly with substance. - AUDIT-004: tests false-greened on filler. Mutation: replacing all 5 bullets with "Stay bash." filler still passed 7/7. Tightened: test 3 requires ≥200 chars + criterion keyword per bullet; test 6 scoped to precompact bullet specifically with fail-closed/fail-open framing. Mutation now correctly fails tests 3+6. Round 2: 10/10 CERTIFIED. 7 quality tests in tests/test-mcp-hook-audit.sh.
Contributor
|
Claude encountered an error —— View job I'll analyze this and get back to you. |
BaseInfinity
added a commit
that referenced
this pull request
Apr 27, 2026
All 5 entries had been implemented but their title cells still read OPEN. Adding DONE markers + commit/PR/version references for archaeology: - #218 MCP-tool hook audit → PR #250, v1.41.1 - #221 post-mortem wizard integration → PR #249, v1.41.0 - #224 prompt-hook-fires-once test → PR #243, v1.38.0 (tests/test-prompt-hook-fires-once.sh) - #225 cleanupPeriodDays guidance → PR #248, v1.40.1 - #226 P1 fake-CI honest labeling → commit 13dccc4 (Option B: judge-consistency caveat; Option A true N-trial deferred to ROADMAP #230 / #212 Option 1 follow-up) Same closure-gap pattern just hit on #209 (PR #255). Five stale markers is enough signal that a roadmap-hygiene check would be worth a small piece of automation — track separately.
2 tasks
BaseInfinity
added a commit
that referenced
this pull request
Apr 27, 2026
All 5 entries had been implemented but their title cells still read OPEN. Adding DONE markers + commit/PR/version references for archaeology: - #218 MCP-tool hook audit → PR #250, v1.41.1 - #221 post-mortem wizard integration → PR #249, v1.41.0 - #224 prompt-hook-fires-once test → PR #243, v1.38.0 (tests/test-prompt-hook-fires-once.sh) - #225 cleanupPeriodDays guidance → PR #248, v1.40.1 - #226 P1 fake-CI honest labeling → commit 13dccc4 (Option B: judge-consistency caveat; Option A true N-trial deferred to ROADMAP #230 / #212 Option 1 follow-up) Same closure-gap pattern just hit on #209 (PR #255). Five stale markers is enough signal that a roadmap-hygiene check would be worth a small piece of automation — track separately.
BaseInfinity
added a commit
that referenced
this pull request
May 5, 2026
ROADMAP #218: CC 2.1.118 added type:'mcp_tool' for hooks. Audited all 5 wizard hooks (sdlc-prompt-check, instructions-loaded-check, tdd-pretool- check, model-effort-check, precompact-seam-check). Conclusion: all stay bash. Per-hook rationale documented under "Known CC Gotchas → MCP-tool hooks audit" so future PRs don't redo the work. Decision criteria: portability (Codex/OpenCode siblings), fail-closed gating (bash exit 2 fails closed; MCP server errors fail open), local-only state (cache files, handoff.json don't surface across tools). Codex round 1: 5/10 NOT CERTIFIED. 4 P1 findings — all real: - AUDIT-001: portability claim cited wrong Codex path (~/.codex/agents/... didn't exist; actual is ~/codex-sdlc-wizard). OpenCode sibling marked 'planned' per ROADMAP #91, not shipped. Fixed. - AUDIT-002: oversimplified "MCP can't gate" claim. CC docs confirm mcp_tool hooks CAN return decision:"block". Real concern: MCP server errors are non-blocking by design — that flips fail-closed (bash) to fail-open (MCP). Rewrote criterion. - AUDIT-003: per-hook rationale was filler ("MCP overkill", "Portability rules"). Each bullet now applies ≥1 criterion explicitly with substance. - AUDIT-004: tests false-greened on filler. Mutation: replacing all 5 bullets with "Stay bash." filler still passed 7/7. Tightened: test 3 requires ≥200 chars + criterion keyword per bullet; test 6 scoped to precompact bullet specifically with fail-closed/fail-open framing. Mutation now correctly fails tests 3+6. Round 2: 10/10 CERTIFIED. 7 quality tests in tests/test-mcp-hook-audit.sh.
BaseInfinity
added a commit
that referenced
this pull request
May 5, 2026
All 5 entries had been implemented but their title cells still read OPEN. Adding DONE markers + commit/PR/version references for archaeology: - #218 MCP-tool hook audit → PR #250, v1.41.1 - #221 post-mortem wizard integration → PR #249, v1.41.0 - #224 prompt-hook-fires-once test → PR #243, v1.38.0 (tests/test-prompt-hook-fires-once.sh) - #225 cleanupPeriodDays guidance → PR #248, v1.40.1 - #226 P1 fake-CI honest labeling → commit 13dccc4 (Option B: judge-consistency caveat; Option A true N-trial deferred to ROADMAP #230 / #212 Option 1 follow-up) Same closure-gap pattern just hit on #209 (PR #255). Five stale markers is enough signal that a roadmap-hygiene check would be worth a small piece of automation — track separately.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
ROADMAP #218: audited all 5 wizard hooks against CC 2.1.118's
type: "mcp_tool"migration option. Conclusion: all stay bash. Per-hook rationale documented in CLAUDE_CODE_SDLC_WIZARD.md → "Known CC Gotchas → MCP-tool hooks audit".Codex Review
~/.codex/agents/...doesn't exist)Test plan