Audit coding-agent instruction drift and verifier health with Waza SKILL.md skillA
Audit coding-agent instruction drift and verifier health with Waza from agentskillexchange/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add agentskillexchange/skills/Audit coding-agent instruction drift and verifier health with Waza@git:20261018.1e411fePins git:20261018.1e411fe in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- agentskillexchange/skills
- Path
skills/audit-coding-agent-instruction-drift-and-verifier-health-with-waza/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261018.1e411fe, committed Oct 18, 2026
- First version recorded
- Oct 15, 2026
- Size
- 1,952 bytes
- Repository stars
- 62
- License
- MIT
Run a bounded, report-only audit of coding-agent settings, instruction reachability, hooks, MCP wiring, and verification evidence with actionable findings.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 ## Documentation - https://github.com/tw93/Waza/blob/main/skills/health/SKILL.md ## Source …
Read the whole file at its exact version.
How to install
mdr add agentskillexchange/skills/Audit coding-agent instruction drift and verifier health with Waza@sha256:f34552991f43a38fThe line at the top of this page pins the label git:20261018.1e411fe, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_5pvsdysk5hu5qmqt)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 15, 2026 and Oct 18, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.1e411fe latest | 2026-10-18 | 1e411fe | 1,952 B | A | view · diff |
| git:20261015.a6c9177 | 2026-10-15 | a6c9177 | 1,898 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (1952 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
agentskillexchange/skills · 62 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5pvsdysk5hu5qmqt GET https://markdownregistry.com/api/v1/resolve?ref=agentskillexchange/skills/Audit coding-agent instruction drift and verifier health with Waza GET https://markdownregistry.com/api/v1/blob/f34552991f43a38f4ab3eb5da6155e821898f7c7fcc15adcb4241a70aeba3749
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.