What is code-audit CLAUDE.md?

Project instructions for Heavy3 Code Audit, a Claude Code skill that sends code reviews to AI models through OpenRouter. It documents local setup, configuration, scripts, and the skill's file structure.

Use them when setting up or modifying the audit skill, its single-model, multi-model council, or free review modes.

They explain how to make the skill discoverable, install its dependency, configure the API key, and run its review scripts correctly.

code-audit CLAUDE.md — Instructions file by heavy3-ai

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/heavy3-ai/code-audit/claude-md

Clone the repo

git clone --depth 1 https://github.com/heavy3-ai/code-audit

Per session 849 This file is loaded in full into every session.

When invoked 849 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.

Model	Per session	Once invoked
Fable 5	$0.00849	$0.00849
Opus 5	$0.00425	$0.00425
Sonnet 5	$0.00170	$0.00170
Haiku 4.5	$0.00085	$0.00085

Measured 2d ago against content hash 093782ca1a50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-audit 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 2d 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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 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.

Project Overview

Heavy3 Code Audit (/h3) is a Claude Code skill providing AI-powered multi-model code reviews via OpenRouter. Modes:

Single (default): DeepSeek V4 Pro, up to 200K tokens
Council: 3-model parallel review (GPT 5.6 Sol + Gemini 3.1 Pro + Grok 4.6), up to 200K tokens
Free: Rotating free models from OpenRouter

Local Development Setup

# Symlink for Claude Code discovery
mkdir -p ~/.claude/skills && ln -sf "$(pwd)/skill" ~/.claude/skills/h3

# Make scripts executable
chmod +x skill/scripts/*.py

# Install dependency
pip install requests

# Required env var
export OPENROUTER_API_KEY="your-key"

Architecture

The skill uses YAML frontmatter + markdown format in SKILL.md to define the skill manifest that Claude reads during /h3 execution.

skill/
├── SKILL.md              # Skill manifest: YAML frontmatter + instructions for Claude
├── config.json           # User config (tier, model, license_key, context limits)
└── scripts/
    ├── review.py         # Lite mode: OpenRouter API calls, prompt templates
    ├── council.py        # Pro mode: 3-parallel reviews with local license check
    ├── license.py        # License activation and verification
    └── list-free-models.py # OpenRouter free model discovery

Data Flow:

User invokes /h3 code|plan|pr <number> in Claude Code
Claude reads SKILL.md, gathers context (git diff, files, docs)
Context compiled to JSON and passed to review script via --context-file
Script calls OpenRouter API, returns review
Claude synthesizes findings, proposes fixes for user approval

Testing the Skill

Automated Tests (pytest)

# Install test dependencies
cd skill && pip install -r requirements-dev.txt

# Run all tests
cd scripts && python -m pytest tests/ -v

# Run specific test file
python -m pytest tests/test_context.py -v
python -m pytest tests/test_review.py -v
python -m pytest tests/test_streaming.py -v
python -m pytest tests/test_council.py -v

Read the full file on GitHub · 94 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.

2d ago First seen · 94 lines · 849 tokens per session scan A 093782ca1a50

Subscribe to this mod's changes

code-audit CLAUDE.md is an instructions file published in the GitHub repository heavy3-ai/code-audit (45 stars, last pushed 20d ago), licensed MIT. It adds 849 tokens to every session, about $0.0042 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 2026-08-30.

Code review Data and AI

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

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

code-audit CLAUDE.md