What is claude-mcp CLAUDE.md?

A set of instructions for Claude Code, an AI coding assistant, when working on a specific TypeScript and JavaScript project. It documents development, testing, type checking, and the project's internal components.

It helps Claude Code start the project, run its Vitest tests, check TypeScript compilation, understand the MCP server, and work with its task-management and execution components.

It gives the assistant the commands and project structure it needs to work consistently. It also records how to run tests and check code without creating output files.

How zhendalf/claude-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zhendalf/claude-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/zhendalf/claude-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/zhendalf/claude-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zhendalf/claude-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/zhendalf/claude-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/zhendalf/claude-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zhendalf/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/zhendalf/claude-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zhendalf/claude-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 904 This file is loaded in full into every session.

When invoked 904 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.

Model	Per session	Once invoked
Fable 5.1	$0.00904	$0.00904
Opus 5	$0.00452	$0.00452
Sonnet 5	$0.00181	$0.00181
Haiku 4.5	$0.00090	$0.00090

Measured 8d ago against content hash 086affae5293, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-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 8d 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 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

npm test - Run the full test suite using Vitest
npm start - Start the MCP server (runs server.js)
MCP_CLAUDE_DEBUG=true npm start - Start with debug logging enabled

Testing

npm test - Run all end-to-end tests
Individual test files are located in tests/ directory

TypeScript Checking

npx tsc --noEmit - Check TypeScript compilation without emitting files (JavaScript files use JSDoc typing)

Architecture

This is an MCP (Model Context Protocol) server that bridges AI tools with Claude Code CLI, enabling conversation continuity and async execution patterns.

Core Components

server.js - Main entry point that:

Registers 6 MCP tools using server.tool() pattern from MCP SDK
Uses direct tool registration (not factory functions) following MCP TypeScript SDK documentation
Orchestrates TaskManager and ClaudeExecutor components

TaskManager (src/managers/TaskManager.js):

Manages async task lifecycle with states: pending → running → completed/failed/cancelled
Stores tasks in memory Map with automatic cleanup after 1 hour
Handles task cancellation by killing spawned Claude CLI processes
Uses randomUUID() for task ID generation

ClaudeExecutor (src/executors/ClaudeExecutor.js):

Discovers Claude CLI installation (checks local ~/.claude/local/claude first, then PATH)
Executes both sync (executeSync) and async (executeAsync) Claude Code calls
Async execution uses --output-format stream-json --verbose for progress tracking
Sync execution uses --output-format json
Always includes --dangerously-skip-permissions flag

MCP Tools Architecture

The server provides 4 tools following conversation branching model:

start - Fresh conversations (sync/async), returns clean text + Response ID or task ID
resume - Continue conversation (sync/async) with previous response ID
status - Polls task progress and results
cancel - Terminates running tasks

Read the full file on GitHub · 92 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.

8d ago First seen · 92 lines · 904 tokens per session scan A 086affae5293

Subscribe to this mod's changes

claude-mcp CLAUDE.md is an instructions file published in the GitHub repository zhendalf/claude-mcp (13 stars, last pushed 1y ago), licensed MIT. It adds 904 tokens to every session, about $0.0045 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.

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 · 7,296 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 · 5,153 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

claude-mcp: Instructions file for Claude Code