hook-ecosystem-auditlisted

<!-- prettier-ignore-start --> **Document Version:** 2.0 **Last Updated:** 2026-03-08 **Status:** ACTIVE <!-- prettier-ignore-end --> # Hook Ecosystem Audit Deep diagnostic of the entire hook ecosystem — Claude Code hooks (`.claude/hooks/`), shared libraries, pre-commit pipeline (`.husky/pre-commit`), and state management. Produces per-category scores, a composite health grade (A-F), trend tracking across runs, and an interactive walkthrough with patch suggestions. **Invocation:** `/hook-ecosystem-audit` ## Critical Rules (MUST follow) 1. **CHECK for saved progress first** (MUST) — resume from `.claude/tmp/hook-audit-progress.json` if it exists and is < 2 hours old. Never re-present findings that were already decided. 2. **ALWAYS run the script first** (MUST) — never generate findings without data. If no saved progress, run the audit script before anything else. 3. **ALWAYS display the dashboard** (MUST) — show to user before walkthrough. 4. **Use conversational Q&A for decisions** (MUST) — present findings in batches, collect decisions via conversation. NEVER use AskUserQuestion. 5. **SAVE progress after every decision** (MUST) — write updated state to progress file immediately. 6. **Show patch suggestions inline** (SHOULD) — with each patchable finding. 7. **Create TDMS entries** (MUST) — for deferred findings via `/add-debt`. 8. **Save decisions** (MUST) — to session log for audit trail. --- ## When to Use - User explicitly invokes `/hook-ecosystem-a