agent-auditor CLAUDE.md

agent-auditor CLAUDE.md is an instructions file for coding agents from basher83/agent-auditor. It costs 917 tokens per session, scanned A, original, MIT.

A set of instructions for auditing agent-related files, including a rule to give audit agents only the file path being audited. It also describes the agent-auditor project and its audit protocol.

In plain words
What is it for?
Use it when invoking audit agents or working in the agent-auditor project, especially for audits of skills, commands, reviews, and other agent instructions.
Why use it?
It keeps audit requests independent so suggestions in the request do not steer the auditor toward expected findings or hide other problems.

Instructions file

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 instructions/basher83/agent-auditor/claude-md
Clone the repo
git clone --depth 1 https://github.com/basher83/agent-auditor

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 agent-auditor CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/basher83/agent-auditor/claude-md.svg)](https://agentmods.dev/instructions/basher83/agent-auditor/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/basher83/agent-auditor/claude-md"><img src="https://agentmods.dev/badge/instructions/basher83/agent-auditor/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 917 This file is loaded in full into every session.
When invoked 917 The same file — it is already loaded in full.
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 $0.00917 $0.00917
Opus 5 $0.00458 $0.00458
Sonnet 5 $0.00183 $0.00183
Haiku 4.5 $0.00092 $0.00092

Measured 3d ago against content hash 869ffbdf7420, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-auditor CLAUDE.md 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 3d 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.

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

⚠️ CRITICAL: Audit Agent Protocol

When invoking ANY audit agent (skill-auditor, command-audit, pr-review, etc.):

  1. ONLY provide the file path - Nothing else
  2. DO NOT mention what you just fixed - No context about recent changes
  3. DO NOT hint at what to look for - No expectations or guidance
  4. DO NOT use words like "test", "verify", "check" - Taints the agent's objectivity
  5. DO NOT explain why you're auditing - Let the agent form independent conclusions

Correct audit invocation:

plugins/meta/meta-claude/skills/skill-factory

WRONG - Tainted audit invocation:

We just fixed effectiveness issues. Can you audit plugins/meta/meta-claude/skills/skill-factory
to verify the triggers are now concrete?

Why this matters: Tainted context skews audit results. The agent will look for what you mentioned instead of finding issues independently. This creates false positives and missed violations.

Remember: Trust but verify. Always audit with untainted context.


Project Overview

agent-auditor is a comprehensive auditing system for Claude Code skills, agents, and components. It provides deterministic Python-based metric extraction and Claude-powered analysis.

See README.md and docs/ for detailed documentation.

Development

  • Tools: See mise.toml for developer tools and tasks
  • Testing: mise exec -- pytest src/tests/
  • Linting: ruff check . and ruff format .
  • Type Checking: mise exec -- pyright src

Key Concepts

  • Deterministic Auditing: Python-based extraction ensures consistent results
  • Effectiveness Validation: Checks compliance and auto-invocation potential
  • Progressive Disclosure: Validates information architecture patterns

Core Principles

Trust But Verify

Never trust claims without verification. This applies to:

Read the full file on GitHub · 117 lines

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. 3d ago First seen · 117 lines · 917 tokens per session scan A 869ffbdf7420

Subscribe to this mod's changes

agent-auditor CLAUDE.md is an instructions file published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 917 tokens to every session, about $0.0046 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 instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens