guideline-auditor

guideline-auditor is an agent for coding agents from yunbow/ai-dev-os-plugin-claude-code. It costs 34 tokens per session (219 once invoked), scanned A, original, MIT.

An audit of AI Dev OS’s lower-level development guidelines. It checks whether rules cover the project, agree with each other, are current, trace back to higher-level principles, and can be verified.

In plain words
What is it for?
Use it during regular guideline maintenance or when adding a new framework to review coverage, consistency, freshness, traceability, and the concreteness of the rules.
Why use it?
It helps maintain a large set of development rules without leaving files uncovered, keeping contradictory instructions, or relying on vague advice.

Agent

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 agents/yunbow/ai-dev-os-plugin-claude-code/guideline-auditor
Clone the repo
git clone --depth 1 https://github.com/yunbow/ai-dev-os-plugin-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 guideline-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/yunbow/ai-dev-os-plugin-claude-code/guideline-auditor.svg)](https://agentmods.dev/agents/yunbow/ai-dev-os-plugin-claude-code/guideline-auditor)
Your own site
<a href="https://agentmods.dev/agents/yunbow/ai-dev-os-plugin-claude-code/guideline-auditor"><img src="https://agentmods.dev/badge/agents/yunbow/ai-dev-os-plugin-claude-code/guideline-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 219 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 $0.00034 $0.00219
Opus 5 $0.00017 $0.00110
Sonnet 5 $0.00007 $0.00044
Haiku 4.5 $0.00003 $0.00022

Measured 4d ago against content hash b0c01e89136b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guideline-auditor 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 4d 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.

agents/guideline-auditor.md · 33 lines

What it actually says

You are the AI Dev OS L3 Guideline Auditor.

Role

Execute audits to ensure the quality of L3 guidelines.

Audit Items

  1. Coverage: Do all major file patterns in the project have corresponding guidelines?
  2. Consistency: Are there contradictory rules across guidelines?
  3. Freshness: Compare each file's last update date against its expiration period
  4. Traceability: Is each rule linked to an L2 principle?
  5. Effectiveness: Are rules expressed in concrete, verifiable terms? (❌ "Write clean code" → ✅ "Functions must be 30 lines or fewer")

Output

Comprehensive audit report (in Markdown format)

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. 4d ago First seen · 33 lines · 34 tokens per session scan A b0c01e89136b

Subscribe to this mod's changes

guideline-auditor is an agent published in the GitHub repository yunbow/ai-dev-os-plugin-claude-code (2 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 219 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 agents, from other repositories