agentmods.dev

code-auditor-mcp: Instructions file for Claude Code

CLAUDE.md

code-auditor-mcp CLAUDE.md is an instructions file for Claude Code from BenAHammond/code-auditor-mcp. It costs 1,694 tokens per session, scanned A, original, MIT.

Development instructions for Code Auditor, a tool that checks code changes against architectural and quality rules.

In plain words
What is it for?
Use it to map a codebase, audit changed files, run the command-line tool or MCP server, and maintain its analyzers and integrations.
Why use it?
It helps an agent understand how to run the project, build it, test it, and audit only the code affected by a change.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is BenAHammond/code-auditor-mcp's own configuration. It tells Claude Code how to work on code-auditor-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything code-auditor-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/ben/playground/code-auditor/app.

not rated 8repo changed 14d ago A scan 1,694 tokens original MIT
View source ↗ BenAHammond/code-auditor-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to BenAHammond/code-auditor-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/BenAHammond/code-auditor-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/BenAHammond/code-auditor-mcp

Made for: Claude Code.

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 code-auditor-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/benahammond/code-auditor-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/benahammond/code-auditor-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/benahammond/code-auditor-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/benahammond/code-auditor-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for code-auditor-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/benahammond/code-auditor-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/benahammond/code-auditor-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,694 This file is loaded in full into every session.
When invoked 1,694 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01694 $0.01694
Opus 5.5 $0.00678 $0.00678
Sonnet 5.5 $0.00339 $0.00339
Haiku 4.5 $0.00169 $0.00169

Measured 14d ago against content hash 703b32b2ea7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-auditor-mcp 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 14d 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 · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 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.

Commands

Development

cd app
npm run dev          # Run CLI in dev mode (tsx src/cli.ts)
npm run dev:server   # Run MCP server with watch mode
npm run dev:mcp      # Run MCP server directly
npm run watch        # Watch TypeScript compilation

Building

cd app
npm run build        # Compile TypeScript to dist/ + copy WASM grammars

Testing

cd app
npm run test         # Run Vitest tests
npm run test:watch   # Run tests in watch mode
npx vitest run path/to/test.spec.ts  # Run specific test file

Running the Tool

cd app
npm run audit        # Run audit tool (after build)
npm run start        # Start MCP server
node dist/cli.js changed --json  # Diff-scoped audit
node dist/cli.js map -p .        # Codebase map

Architecture Overview

Code Auditor enforces architectural invariants and code quality rules inside an AI agent's edit loop. It integrates with Claude via Model Context Protocol (MCP), a CLI, and a Claude Code plugin.

Core Components

  1. Analyzers (app/src/analyzers/)

    • Functional pattern: each analyzer is a function returning arrays of violations
    • Analyzers process tree-sitter ASTs via adapterBridge.ts
    • Current analyzers: SOLID, DRY, data access, React, documentation, schema, invariants

  2. Language Layer (app/src/languages/)

    • LanguageAdapter interface (23 methods) — the single seam for language support
    • adapterBridge.ts — synchronous facade over tree-sitter parsers
    • tree-sitter/parser.ts — web-tree-sitter WASM loader (initParsers(), getParser())
    • LanguageRegistry — singleton; adapters registered by initializeLanguages()
    • Two-phase init: initializeLanguages() (sync, registers adapters) then initParsers() (async, loads WASM grammars). Both required before any parsing.
    • Adapters: TreeSitterTypeScriptAdapter (.ts/.tsx/.js/.jsx), TreeSitterGoAdapter (.go)
    • WASM grammars at dist/grammars/ — shipped in the npm package; zero native compilation

Read the full file on GitHub · 142 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. 14d ago Changed · +3 lines · +26 tokens per session 703b32b2ea7f
  2. 25d ago Changed · -2 tokens per session 50317ce3ea95
  3. 1mo ago Changed · +15 tokens per session d4306242a373
  4. 1mo ago Changed · +1 lines · +30 tokens per session fa1cceda7790
  5. 2mo ago First seen · 138 lines · 1,625 tokens per session scan A 69672ab36c30

Subscribe to this mod's changes

code-auditor-mcp CLAUDE.md is an instructions file published in the GitHub repository BenAHammond/code-auditor-mcp (8 stars, last pushed 5d ago), licensed MIT. It adds 1,694 tokens to every session, about $0.0068 per session on Opus 5.5. 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.

Code review
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 · 9,715 tokens

next.js AGENTS.md

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens