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 in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application code or reviewing PRs.
- installs 8w
- 3,064
- 30-day movement
- starts with the next reading
- Related entries
- 4
- Connections
- 0
A SKILL.md agent skill that runs a budget-aware engineering health audit of AI agent setups, covering instruction/config drift, hooks and MCP servers, verifier surfaces, and AI maintainability. It works across Claude, Codex, and Pi configurations, collects evidence via read-only probes, and produces a report-only audit with prioritized findings.
Use it when you suspect your agent instructions, configs, or MCP setup have drifted or degraded and want a structured, evidence-based audit rather than ad-hoc checking.
Use it to
- Audit Claude, Codex, or Pi agent configs for drift
- Live-check MCP servers and hooks
- Check verifier coverage and validation drift
- Assess AI maintainability of a codebase
- Audit long-running agent stop conditions
For Developers maintaining AI coding agent setups
- Host repository
- tw93/Waza
- Installs, lifetime
- 15k
- Installs, 8 weeks
- 3,064
- Host stars
- 7,044
- Host language
- Python