guardrail_audit SKILL.md skillA
guardrail_audit from theafh/ai-modules is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add theafh/ai-modules/guardrail_audit@v1.0.4Pins v1.0.4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- theafh/ai-modules
- Path
plugins/ai_dev/skills/guardrail_audit/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.4, committed Sep 5, 2026
- First version recorded
- Aug 5, 2026
- Size
- 10,109 bytes
- Repository stars
- 39
- License
- MIT
Read-only audit of a repository's existing guardrail docs. It surfaces doc-vs-doc contradictions and doc-vs-code divergences ranked by the guardrail hierarchy, plus grounded missing-doc proposals where repo substance warrants an absent doc. Edits nothing; every finding carries evidence and a reconcile recommendation, and the run ends by asking how to proceed. Use when auditing, health-checking, or retrofitting guardrail docs against each other and the codebase; when a freshly adopted…
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
# guardrail_audit <guardrail_audit_skill> <role> guardrail_audit is the read-only audit sibling of the `guardrail` hub: it surfaces divergences among a repository's *existing* guardrail docs, and between those docs and the established codebase, ranked by the hub's hierarchy, and proposes grounded missing docs where repo substance plainly warrants an absent type. It edits nothing; every finding and proposal carries evidence and a reconcile recommendation, and the run ends by asking the user how to proceed. Its main use case is retrofitting: a guardrail freshly adopted into a mature repository, where the audit flags the pre-existing divergences that forward-looking enforcement cannot reach. </role> <when_to_activate> Activate when the user wants the repo's *existing* guardrail docs audited: - "Audit the guardrails" / "do the guardrail docs still match the code?" / "health-check CHARTER.md against the repo." - "Retrofit a charter into this mature repo, so what already diverges?" - "Are ARCHITECTURE.md / TESTING.md / SECURITY.md consistent with each other and with CLAUDE.md?" …
Read the whole file at its exact version.
How to install
mdr add theafh/ai-modules/guardrail_audit@sha256:12a1573c02c2167cThe line at the top of this page pins the label v1.0.4, 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_pmxdlk6unowar2uu)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 5, 2026 and Sep 5, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.4 latest | 2026-09-05 | e04ae6b | 10,109 B | A | view · diff |
| v1.0.3 | 2026-09-05 | a750d17 | 10,155 B | A | view · diff |
| v1.0.2 | 2026-08-20 | 962b9c1 | 10,155 B | A | view · diff |
| v1.0.1 | 2026-08-09 | 2d28736 | 8,744 B | A | view · diff |
| v1.0.0 | 2026-08-05 | 7ba76da | 6,279 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 (10109 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
theafh/ai-modules · 39 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pmxdlk6unowar2uu GET https://markdownregistry.com/api/v1/resolve?ref=theafh/ai-modules/guardrail_audit GET https://markdownregistry.com/api/v1/blob/12a1573c02c2167cb7e3e8b7943d3b6ccc320515cf07a299b6f5ff61c2c6d635
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.