Audit coding-agent instruction drift and verifier health with Waza
Run a bounded, report-only audit of coding-agent settings, instruction reachability, hooks, MCP wiring, and verification evidence with actionable findings.
Prerequisites
SKILL.md-compatible coding agent; Node.js/npx for skills installation or supported host plugin; Bash and trusted Python 3 for complete collector coverage; project-local read access
Installation
Install or set up from the source-backed instructions:
Install skills: npx skills add tw93/Waza -a claude-code codex cursor -g -y. Invoke the installed health skill by name and request instructions-only scope when session history is out of scope. Claude Code plugin alternative: /plugin marketplace add tw93/Waza then /plugin install waza@waza; invoke /waza:health. Codex plugin alternative: codex plugin marketplace add tw93/Waza then codex plugin add waza@waza. Read the installed health/SKILL.md and use its collector launcher; no optional persistent rules or statusline setup is required.
- Source: https://github.com/tw93/Waza