health
Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application code or reviewing PRs.
Pinned to revision 492b9e5587be, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/health/SKILL.md
- skills/health/evals/cases/audit-agent-config.yaml
- skills/health/evals/cases/audit-mcp-config.yaml
- skills/health/evals/eval.yaml
- skills/health/references/context-engineering.md
- skills/health/references/long-running-agents.md
- skills/health/references/maintainability-findings.md
- skills/health/references/safety-baseline.md
- skills/health/scripts/block-pipe-to-shell.py
- skills/health/scripts/check-agent-context.sh
- skills/health/scripts/check-doc-refs.sh
- skills/health/scripts/check-maintainability.sh
- skills/health/scripts/check-verifier-output.sh
- skills/health/scripts/check_agent_context.py
- skills/health/scripts/check_doc_refs.py
- skills/health/scripts/check_maintainability.py
- skills/health/scripts/check_verifier_output.py
- skills/health/scripts/collect-data.sh
- skills/health/scripts/conversation_audit.py
- skills/health/scripts/read_skill_description.py
- skills/health/scripts/run-health.ps1
- skills/health/scripts/scan_skill_security.py
Every link opens the file at its source, pinned to the revision this page describes.