lightweight-github-mcp: Instructions file for Claude Code

CLAUDE.md

lightweight-github-mcp CLAUDE.md is an instructions file for Claude Code from ham0215/lightweight-github-mcp. It costs 800 tokens per session, scanned A, original, MIT.

A project guide for Claude Code in a lightweight GitHub MCP repository. The repository is a small server that limits which tools from GitHub's official MCP server are exposed to an AI coding agent.

In plain words
What is it for?
Use it to install dependencies, build, run, develop, and inspect the lightweight GitHub MCP server.
Why use it?
It gives an agent the project background, required software, commands, and architecture needed to work on the codebase. MCP is a way for an AI agent to call external tools and services.

Instructions file for Claude Code

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

This is ham0215/lightweight-github-mcp's own configuration. It tells Claude Code how to work on lightweight-github-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 lightweight-github-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ham0215/lightweight-github-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/ham0215/lightweight-github-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ham0215/lightweight-github-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 lightweight-github-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ham0215/lightweight-github-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ham0215/lightweight-github-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ham0215/lightweight-github-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ham0215/lightweight-github-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 lightweight-github-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ham0215/lightweight-github-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ham0215/lightweight-github-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 800 This file is loaded in full into every session.
When invoked 800 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 $0.00800 $0.00800
Opus 5.5 $0.00320 $0.00320
Sonnet 5.5 $0.00160 $0.00160
Haiku 4.5 $0.00080 $0.00080

Measured 2mo ago against content hash 96043e85fc66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lightweight-github-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 2mo 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 · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 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

Lightweight GitHub MCP is a proxy server that wraps github/github-mcp-server (GitHub's official MCP server) and exposes only whitelisted tools via YAML configuration. This dramatically reduces context consumption (100+ tools → 10-20 tools).

Prerequisites: Docker must be installed and running.

Build and Run Commands

# Install dependencies
npm install

# Build
npm run build

# Development mode (watch)
npm run dev

# Run the server
npm start

# Test with MCP Inspector
npx @modelcontextprotocol/inspector node dist/index.js

Architecture

Claude Desktop/Code
        │ MCP Protocol (stdio)
        ▼
┌─────────────────────────────┐
│  lightweight-github-mcp     │
│  ┌─────────┐  ┌──────────┐  │
│  │MCP      │→ │Tool      │→ │ config.yaml (allowedTools)
│  │Server   │  │Filter    │  │
│  └─────────┘  └──────────┘  │
│         ↑          │        │
│         │    ┌─────▼─────┐  │
│         │    │MCP Client │  │
│         │    └─────┬─────┘  │
└─────────┼──────────┼────────┘
          │          │ spawn Docker container
          │          ▼
          │  github/github-mcp-server (Docker, ~100 tools)
          │
    Claude requests

Key Components

  • src/index.ts - Entry point, config loading, server initialization
  • src/server.ts - MCP server implementation, tool filtering, meta-tool handlers
  • src/upstream-client.ts - Child process management for upstream GitHub MCP
  • src/config.ts - YAML configuration loading and validation
  • config.yaml - Tool whitelist configuration

Meta-Tools (Always Available)

The proxy provides four built-in meta-tools that are always exposed:

  • list_all_upstream_tools - List all upstream tools (allowed + blocked)
  • list_blocked_tools - List blocked tools by category
  • search_upstream_tools - Search upstream tools by keyword
  • get_tool_info - Get details about a specific tool

Read the full file on GitHub · 118 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. 2mo ago First seen · 118 lines · 800 tokens per session scan A 96043e85fc66

Subscribe to this mod's changes

lightweight-github-mcp CLAUDE.md is an instructions file published in the GitHub repository ham0215/lightweight-github-mcp (0 stars, last pushed 10mo ago), licensed MIT. It adds 800 tokens to every session, about $0.0032 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.

Related

lightweight-github-mcp CLAUDE.md compared with instructions from other repositories

lightweight-github-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lightweight-github-mcp CLAUDE.mdham0215/lightweight-github-mcpInstructions file010mo agoMITA800Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode