# Instructions Audit

> Audit and improve AGENTS.md project instructions (and legacy CLAUDE.md). Use when the user asks to check, audit, update, improve, fix, restructure, or clean up AGENTS.md / CLAUDE.md, or mentions "agent memory", "project memory", "project instructions", "instruction file", "instruction maintenance", "instruction structure", or filenames like AGENTS.md, agents.md, CLAUDE.md. Scans the repo, evaluates quality against a rubric, prints a report, and proposes targeted edits. When the repo still uses CLAUDE.md only, also proposes migrating to AGENTS.md. Arguments: none (full audit), "recent" (scope to the last 5 commits), "last <N commits", or "since <ref" — scoped runs skip rubric scoring and propose only updates surfaced by that commit range (e.g. "audit recent changes", "update AGENTS.md for the last 3 commits").

## Facts
- Page: https://tashan.sh/capability/skill-dotknewt-instructions-audit
- tashan id: skill:dotknewt/instructions-audit
- Source: https://github.com/dotknewt/awesome-agency
- Type: skill
- Category: other
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 96.0
- Freshness: 92.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r instructions-audit ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.