ai-dev-os-audit

ai-dev-os-audit is a skill for Claude Code from yunbow/ai-dev-os-plugin-claude-code. It costs 46 tokens per session (464 once invoked), scanned A, original, MIT.

An audit for an AI Dev OS, a four-layer set of project rules and guidance for coding agents. It checks dependencies between layers, outdated files, links between rules, missing coverage, and contradictions.

In plain words
What is it for?
Checking rule-layer structure, file freshness, traceability, referenced files, directory coverage, and consistency across AI Dev OS documentation.
Why use it?
It reveals when the project's guidance has become outdated, incomplete, disconnected, or inconsistent. This helps maintain the rule system during monthly or quarterly maintenance.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; mentions CLAUDE.md; mentions Claude Code.

Part of the ai-dev-os plugin — 11 skills, 3 agents, 3 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-audit
Any agent
npx skills add yunbow/ai-dev-os-plugin-claude-code --skill ai-dev-os-audit
Clone the repo
git clone --depth 1 https://github.com/yunbow/ai-dev-os-plugin-claude-code

Made for: Claude Code.

Or install ai-dev-os, the plugin that ships this one along with the rest of its 11 skills, 3 agents, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-dev-os-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-audit.svg)](https://agentmods.dev/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-audit)
Your own site
<a href="https://agentmods.dev/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-audit"><img src="https://agentmods.dev/badge/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00464
Opus 5 $0.00023 $0.00232
Sonnet 5 $0.00009 $0.00093
Haiku 4.5 $0.00005 $0.00046

Measured 5d ago against content hash 7b4c3ae96420, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ai-dev-os-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ai-dev-os-audit/SKILL.md · 71 lines

What it actually says

AI Dev OS 4-Layer Health Audit

Audit Items

1. Dependency Rules (Clean Architecture Principle)

  • Do L1 files contain tool-specific terms? ("Claude Code", "Cursor", "Next.js", etc.)
  • Do L2 files contain framework-specific implementation details?
  • Is the one-way dependency L1 → L2 → L3 → L4 maintained?

2. Expiration Check

  • L1: Last updated more than 5 years ago?
  • L2: Last updated more than 3 years ago?
  • L3: Last updated more than 12 months ago?
  • L4: Last updated more than 4 months ago?
  • Use git log to get the last update date for each file

3. Traceability

  • Does each L3 guideline have a link to an L2 principle?
  • Does each L4 AI Frame have a reference to an L3 guideline?
  • Are there orphaned rules (not linked to any principle)?

4. Coverage

  • Do all files referenced in CLAUDE.md actually exist?
  • Are there guidelines for the project's major file patterns?
  • Are there mapped guidelines for each directory under src/?

5. Consistency

  • Are there contradictory rules across multiple guidelines?
  • Are naming conventions consistent across all files?

Output Format

## AI Dev OS Health Audit Report

### Score: N/100

### Layer Health
| Layer | Files | Coverage | Freshness | Dependencies | Score |
|-------|-------|----------|-----------|-------------|-------|

### Issues Found
| Severity | Issue | Location | Action |
|----------|-------|----------|--------|

### Recommendations
1. [Priority: High] ...
2. [Priority: Medium] ...

Language

Respond in the same language as the project's CLAUDE.md file.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 71 lines · 46 tokens per session scan A 7b4c3ae96420

Subscribe to this mod's changes

ai-dev-os-audit is a skill published in the GitHub repository yunbow/ai-dev-os-plugin-claude-code (2 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 464 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

guideline-checker

Automatically check whether git diff contents comply with project guidelines after code changes. Run at coding completion or before committing.

yunbow/ai-dev-os-rules-typescript · 27 tokens

type-check

Run TypeScript type checking and ESLint, identify error locations, and provide fix suggestions. Used for quality assurance after implementation.

yunbow/ai-dev-os-rules-typescript · 28 tokens

stale-brain

Audit AI agent memory and instruction files: CLAUDE.md, AGENTS.md, .cursorrules, GEMINI.md, copilot-instructions.md and every other major agent's memory files (13 agents, 18+ file locations) against the live repository. Use when the user runs /stale-brain or asks to audit, verify, refresh, lint, or fix agent memory…

stalebrainlabs/stalebrain · 185 tokens

project-spine-kickoff

Use when the user wants to set up Project Spine for a new project — phrases like "new client project", "kickoff", "create AGENTS.md from scratch", "generate agent instructions for this repo", "set up project context". Runs spine init → edits brief → spine compile → reviews outputs. For stale files use…

PetriLahdelma/project-spine · 84 tokens

project-spine-drift

Use when the user mentions drift, says AGENTS.md / CLAUDE.md / copilot-instructions / Cursor rules are "stale" or "out of date", asks about CI catching docs drift, or says "check if my spine is still current". Runs spine drift check, interprets each drift category, and guides resolution. For initial setup use…

PetriLahdelma/project-spine · 87 tokens

project-spine

Use when the user mentions AGENTS.md, CLAUDE.md, copilot-instructions, Cursor rules, project brief, context for coding agents, agency kickoff, onboarding a new project, or asks "how do I set up Project Spine". This is the orientation skill — reach for it FIRST when the user's intent involves Project Spine, then chain…

PetriLahdelma/project-spine · 80 tokens