Health

Runs a structured audit of your Claude Code and Codex setup to catch instruction drift, missing verifiers, failing MCP servers, and AI maintainability problems before they rot your codebase. It tiers projects by size (simple/standard/complex) and only runs deep inspections when you ask for them or when the summary pass finds critical ambiguity. The collector script checks agent config across AGENTS.md and runtime files, tests MCP tools live, and flags hotspots where AI-written code is getting hard to maintain. Findings come with copy-paste fixes, not vague suggestions. Useful when Claude starts ignoring instructions, when validation commands go stale, or when you suspect your agent setup has drifted from reality.

skills.sh installs: 16.4K
GitHub stars: 7.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tw93/waza --skill health --agent claude-code

Installs into .claude/skills of the current project.

Files

Health: Agent-Assisted Engineering Health

Prefix your first line with 🥷 inline, not as its own paragraph.

Audit the current project's agent setup and AI coding maintainability against this framework: agent config → instruction surfaces → tools/runtime → verifiers → maintainability

Find violations. Identify the misaligned layer. Calibrate to evidence and risk, not repository size.

Outcome Contract

Outcome: a budget-aware health report that separates agent configuration risk from AI maintainability risk.
Done when: each finding names the misaligned layer, the concrete evidence, and a copy-pasteable action or diagnostic command.
Evidence: collected health script output, tracked project instructions, runtime config summaries, verifier logs, hooks/MCP surfaces, and read-only live probes when needed.
Output: prioritized findings with status, impact, and next action, or a clear clean bill with residual risk.

Two lanes share one report:

SKILL.md on GitHub