git-context-mcp: Instructions file for Claude Code

CLAUDE.md

git-context-mcp CLAUDE.md is an instructions file for Claude Code from muhannad-hash/git-context-mcp. It costs 500 tokens per session, scanned A, original, MIT.

An MCP server that explains why code exists by combining Git history with GitHub context. It can connect a line, file, commit, or search term to authors, pull requests, and issues.

In plain words
What is it for?
Finding who wrote a line, understanding a commit’s full story, reviewing a file’s history, searching commits by keyword, and listing a file’s contributors.
Why use it?
It saves developers from piecing together code history manually across commit logs, blame output, pull requests, and issue trackers. This can reveal the original reason for a change before modifying it.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is muhannad-hash/git-context-mcp's own configuration. It tells Claude Code how to work on git-context-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 git-context-mcp configures →

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/muhannad-hash/git-context-mcp/claude-md.svg)](https://agentmods.dev/instructions/muhannad-hash/git-context-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/muhannad-hash/git-context-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/muhannad-hash/git-context-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 500 This file is loaded in full into every session.
When invoked 500 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00500 $0.00500
Opus 5 $0.00250 $0.00250
Sonnet 5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured 6d ago against content hash f4273d47b112, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

git-context-mcp CLAUDE.md scanned grade A with 1 finding 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 6d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- All git operations use `execSync` with `stdio: pipe` so errors return `""` instead of throwing
CLAUDE.md · 57 lines

What it actually says

git-context-mcp

An MCP server that answers the question every developer asks: "why does this code exist?"

What this project does

TypeScript MCP server built with @modelcontextprotocol/sdk. It exposes 5 tools that combine local git operations (git blame, git log, git show) with GitHub API calls via the gh CLI to surface the full story behind any piece of code — the commit, the PR, and the original issue.

Project structure

src/index.ts      — entire server: helpers, tool handlers, server setup
dist/             — compiled output (gitignored)

Tools exposed

Tool Purpose
blame_context File + line range → who wrote it + PR + linked issues
commit_story Commit hash → full narrative (message, PR, issues)
file_history File → last N commits, each with PR context
search_commits Keyword → matching commits + PR/issue context
file_contributors File → ranked author table (commits, lines owned, date range)

Key implementation details

  • All git operations use execSync with stdio: pipe so errors return "" instead of throwing
  • GitHub API calls shell to gh api — no token needed beyond gh auth login
  • findPRForCommit uses the GitHub commits→pulls endpoint (/repos/:owner/:repo/commits/:hash/pulls)
  • Issue refs are extracted from PR bodies via #NNN and /issues/NNN patterns
  • blame_context uses git blame -p (porcelain) and parses the structured block format

Dev commands

npm run build   # tsc compile to dist/
npm run dev     # tsc --watch
npm start       # run the compiled server

Testing with Claude Code

Add to ~/.claude/claude_mcp_config.json:

{
  "mcpServers": {
    "git-context": {
      "command": "node",
      "args": ["<absolute-path>/dist/index.js"]
    }
  }
}

Then in any repo ask Claude: "Why does line 42 of src/auth.ts exist?"

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. 6d ago First seen · 57 lines · 500 tokens per session scan A f4273d47b112

Subscribe to this mod's changes

git-context-mcp CLAUDE.md is an instructions file published in the GitHub repository muhannad-hash/git-context-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 500 tokens to every session, about $0.0025 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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 · 5,182 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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

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