mcp-server-git: Instructions file for Claude Code

CLAUDE.md

mcp-server-git CLAUDE.md is an instructions file for Claude Code from a-g-e-n-t-s/mcp-server-git. It costs 11,772 tokens per session, scanned A, original, Apache-2.0.

A set of Claude Code instructions for developing git-mcp-server, an MCP server that exposes Git-related tools. MCP is a standard way for an AI coding agent to call external tools.

In plain words
What is it for?
Use it when contributing to git-mcp-server, especially when implementing tool or resource logic and handling errors.
Why use it?
It defines the project's architecture, error-handling rules, file-synchronization rule, and workflow for adding tools and resources.

Instructions file for Claude Code

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

This is a-g-e-n-t-s/mcp-server-git's own configuration. It tells Claude Code how to work on mcp-server-git 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 mcp-server-git configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is } from '../utils/json-response-formatter.js';.

Reuse

Borrowing it

Nothing to install: this file belongs to a-g-e-n-t-s/mcp-server-git. 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/a-g-e-n-t-s/mcp-server-git/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/a-g-e-n-t-s/mcp-server-git

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 mcp-server-git CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/a-g-e-n-t-s/mcp-server-git/claude-md.svg)](https://agentmods.dev/instructions/a-g-e-n-t-s/mcp-server-git/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/a-g-e-n-t-s/mcp-server-git/claude-md"><img src="https://agentmods.dev/badge/instructions/a-g-e-n-t-s/mcp-server-git/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 11,772 This file is loaded in full into every session.
When invoked 11,772 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 $0.11772 $0.11772
Opus 5 $0.05886 $0.05886
Sonnet 5 $0.02354 $0.02354
Haiku 4.5 $0.01177 $0.01177

Measured 7d ago against content hash e753c6113ad9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-server-git 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 7d 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 · 1,159 lines

How it starts

The opening of the file, as written. The whole thing — 1,159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Protocol & Architectural Mandate

Version: 2.4.1 Target Project: git-mcp-server Last Updated: 2025-10-11

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

Note on File Synchronization: This file (AGENTS.md), along with CLAUDE.md and .clinerules/AGENTS.md, are hard-linked on the filesystem for tool compatibility (e.g., Cline does not work with symlinks). Edit only the root AGENTS.md – changes will automatically propagate to the other copies. DO NOT TOUCH THE OTHER TWO AGENTS.md & CLAUDE.md FILES.


I. Core Principles (Non‑Negotiable)

  1. The Logic Throws, The Handler Catches

    • Your Task (Logic):
      • Tools: Implement pure, stateless business logic inside the logic function of a ToolDefinition.
      • Resources: Implement pure, stateless read logic inside the logic function of a ResourceDefinition.
      • Do not add try...catch in these logic functions.
    • On Failure: You must throw new McpError(...) with the appropriate JsonRpcErrorCode and context.
    • Framework's Job (Handlers):
      • Tools are wrapped by createMcpToolHandler, which creates the RequestContext, measures execution via measureToolExecution, formats the response, and is the only place that catches errors.
      • Resources are wrapped by registerResource (resourceHandlerFactory). The handler validates params, invokes logic, applies responseFormatter (defaulting to JSON), and catches errors.
  2. Full‑Stack Observability

    • Tracing: OpenTelemetry is preconfigured. Logs and errors are automatically correlated to traces.
    • Performance: measureToolExecution automatically records duration, success, payload sizes, and error codes for every tool call.
    • No Manual Instrumentation: Do not add custom spans in your logic. Use the provided utilities and structured logging. The framework handles the single wrapper span per tool invocation.

Read the full file on GitHub · 1,159 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. 7d ago First seen · 1,159 lines · 11,772 tokens per session scan A e753c6113ad9

Subscribe to this mod's changes

mcp-server-git CLAUDE.md is an instructions file published in the GitHub repository a-g-e-n-t-s/mcp-server-git (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 11,772 tokens to every session, about $0.0589 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.

Related

Other instructions, from other repositories

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

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

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

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

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