git-mcp-server: Instructions file for Claude Code

CLAUDE.md

git-mcp-server CLAUDE.md is an instructions file for Claude Code from cyanheads/git-mcp-server. It costs 5,712 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for contributing to a Git MCP server, including its architecture and rules for implementing tools and resources.

In plain words
What is it for?
Use them when adding or changing Git-related MCP tools, resources, handlers, or supporting code in this repository.
Why use it?
They keep business logic separate from error handling and require changes to follow the project's established handlers, dependency structure, and file conventions.

Instructions file for Claude Code

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

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { ToolDefinition } from '../utils/toolDefinition.js';.

Reuse

Borrowing it

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

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-mcp-server CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cyanheads/git-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/git-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,712 This file is loaded in full into every session.
When invoked 5,712 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 $0.05712 $0.05712
Opus 5.5 $0.02285 $0.02285
Sonnet 5.5 $0.01142 $0.01142
Haiku 4.5 $0.00571 $0.00571

Measured 2mo ago against content hash 38c9bc2e4444, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-mcp-server 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 · 550 lines

How it starts

The opening of the file, as written. The whole thing — 550 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Protocol & Architectural Mandate

Version: 2.15.3 Target Project: git-mcp-server Last Updated: 2026-08-24

This document defines the operational rules for contributing to this codebase. Follow it exactly.

Note on File Synchronization: AGENTS.md is a symlink to CLAUDE.md. Edit only CLAUDE.md — AGENTS.md will reflect changes automatically.


I. Core Principles (Non-Negotiable)

  1. The Logic Throws, The Handler Catches

    • Tools: Implement pure, stateless business logic inside tool logic functions. No try/catch blocks.
    • Resources: Same rule — pure read logic, no try/catch.
    • On Failure: Throw new McpError(...) with the appropriate JsonRpcErrorCode and context.
    • Framework's Job:
      • createMcpToolHandler wraps tool logic: creates RequestContext, measures execution via measureToolExecution, formats the response, catches errors.
      • createToolHandler wraps git-specific logic: resolves DI dependencies and working directory before calling your pure logic.
      • Resource handlers (resourceHandlerFactory) validate params, invoke logic, apply responseFormatter, and catch errors.
  2. Full-Stack Observability

    • OpenTelemetry is preconfigured. Logs and errors are automatically correlated to traces.
    • measureToolExecution automatically records duration, success, payload sizes, and error codes for every tool call.
    • Do not add custom spans in tool/resource logic. The framework handles instrumentation.
  3. Structured, Traceable Operations

    • Tool logic receives dependencies via ToolLogicDependencies (which includes appContext and sdkContext).
    • appContext (RequestContext): Internal logging/tracing context with requestId, sessionId, tenantId, traceId.
    • sdkContext (SdkContext): MCP SDK protocol capabilities — signal, sendNotification, sendRequest, authInfo.
    • Pass appContext through your internal call stack. Use the global logger with appContext in every log call.

Read the full file on GitHub · 550 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 · 550 lines · 5,712 tokens per session scan A 38c9bc2e4444

Subscribe to this mod's changes

git-mcp-server CLAUDE.md is an instructions file published in the GitHub repository cyanheads/git-mcp-server (245 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 5,712 tokens to every session, about $0.0228 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 2026-08-30.

Related

git-mcp-server CLAUDE.md compared with instructions from other repositories

git-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
git-mcp-server CLAUDE.mdcyanheads/git-mcp-serverInstructions file2451mo agoApache-2.0A5,712Claude 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