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.
npx agentmods add instructions/toolprint/cco-mcp/claude-mdgit clone --depth 1 https://github.com/toolprint/cco-mcpWrote 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.
[](https://agentmods.dev/instructions/toolprint/cco-mcp/claude-md)<a href="https://agentmods.dev/instructions/toolprint/cco-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/toolprint/cco-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01286 | $0.01286 |
| Opus 5 | $0.00643 | $0.00643 |
| Sonnet 5 | $0.00257 | $0.00257 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
cco-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 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.
How it starts
The opening of the file, as written. The whole thing — 235 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
CCO-MCP (Claude Code Oversight - Model Context Protocol) is a comprehensive audit and approval system for Claude Code tool calls. It consists of:
- A Node.js/TypeScript MCP server backend with Express REST API
- A React/TypeScript web dashboard UI
- Real-time updates via Server-Sent Events (SSE)
- Rule-based approval configuration system
Development Commands
Build Commands
# Build everything (backend + UI)
just build-all
# or
pnpm build:all
# Build backend only
just build
# or
pnpm build
# Build UI only
just build-ui
# or
pnpm build:ui
# Watch mode for backend
just build-watch
# or
pnpm build:watch
Development Commands
# Run both backend and UI in development mode
just dev-all
# or
pnpm dev:all
# Run backend only
just dev
# or
pnpm dev
# Run UI only
just dev-ui
# or
pnpm dev:ui
# Inspect MCP server
just inspect
# or
pnpm inspect
Code Quality Commands
# Format code
just format
# or
pnpm format
# Check formatting
just format-check
# or
pnpm format:check
# Lint
just lint
# or
pnpm lint
Testing Commands
# Run tests (currently echoes no tests configured)
just test
# or
pnpm test
# E2E tests with recording options
just e2e-test # Without recording
just e2e-test-browser # Browser recording only
just e2e-test-terminal # Terminal recording only
just e2e-test-full # Both recordings
Architecture Overview
Backend Architecture
The backend follows a modular architecture:
-
MCP Integration (
src/server.ts)- Implements the MCP server with
approval_prompttool - Handles polling mechanism for approval/denial
- Integrates with the audit service
- Implements the MCP server with
-
Express API (
src/app.ts)- REST endpoints for audit logs and configuration
- SSE endpoint for real-time updates
- Static file serving for UI in production
-
Audit Service (
src/audit/)
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.
- 5d ago First seen · 235 lines · 1,286 tokens per session scan A c4f768d2227b
cco-mcp CLAUDE.md is an instructions file published in the GitHub repository toolprint/cco-mcp (19 stars, last pushed 1y ago), licensed MIT. It adds 1,286 tokens to every session, about $0.0064 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.
Other instructions, from other repositories
vibe-workspace CLAUDE.md
Instructions for toolprint/vibe-workspace, covering claude.md, core commands, development workflow, build and development and testing and validation.
ratel AGENTS.md
AGENTS.md instructions for ratel-ai/ratel, covering agents.md — working in the ratel repo, build & test, rust, ts and python (from src/sdk/python/; needs uv).
OpenKB AGENTS.md
AGENTS.md instructions for VectifyAI/OpenKB, covering agents.md — openkb map for coding agents, read next, dev commands, module map (openkb/) and hard invariants.
mastra AGENTS.md
AGENTS.md instructions for mastra-ai/mastra: Unless asked, don't inspect reference or modify examples. Use the most-specific AGENTS.md; for package work, read packages/ /AGENTS.md first.
mesh-llm AGENTS.md
AGENTS.md instructions for Mesh-LLM/mesh-llm, covering agent notes, repo overview, key docs, public website and building.
ACCESSIBILITY.md AGENTS.md
AGENTS.md instructions for mgifford/ACCESSIBILITY.md, covering repository instructions for ai coding agents, scope, when each instruction file is useful, project mission and status and required project context.