Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/atla-digital/mcp-gitlab/claude-mdgit clone --depth 1 https://github.com/atla-digital/mcp-gitlabWrote 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.
[](https://agentmods.dev/instructions/atla-digital/mcp-gitlab/claude-md)<a href="https://agentmods.dev/instructions/atla-digital/mcp-gitlab/claude-md"><img src="https://agentmods.dev/badge/instructions/atla-digital/mcp-gitlab/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04273 | $0.04273 |
| Opus 5 | $0.02136 | $0.02136 |
| Sonnet 5 | $0.00855 | $0.00855 |
| Haiku 4.5 | $0.00427 | $0.00427 |
Grade A, and why
mcp-gitlab 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:3001/mcp \ How it starts
The opening of the file, as written. The whole thing — 511 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.
Development Commands
Build and Development
npm run build- Compile TypeScript and make executablenpm run prepare- Runs build (used by npm lifecycle)npm run watch- Watch TypeScript files for changes and recompilenpm run inspector- Start MCP inspector for debugging server
Code Quality & Linting
# Lint and format code
npm run lint # Check linting issues
npm run lint:fix # Auto-fix linting issues
npm run format # Format code with Prettier
npm run format:check # Check code formatting
CI/CD & Documentation
# Install git hooks for automatic documentation generation
npm run install-hooks
# Generate tool documentation manually
npm run generate-docs
Architecture Overview
This is a Model Context Protocol (MCP) server for GitLab integration built in TypeScript with Streamable HTTP as the primary transport. The server enables AI assistants to interact with GitLab repositories through a comprehensive set of tools.
Streamable HTTP Transport
The server implements the Streamable HTTP MCP transport protocol, running as an HTTP service on port 3001. This allows for:
- Direct HTTP-based MCP communication
- Better performance and reliability than stdio/process-based transports
- Support for multiple concurrent clients
- Easy deployment in containerized environments
Core Architecture
Main Entry Point: src/server/streamable-http-server.ts
- Implements GitLabStreamableHttpServer class with HTTP transport
- Creates axios instances with GitLab API authentication per session
- Sets up request handlers for tools, resources, and capabilities
Tool Organization: The codebase is organized into four main functional domains:
- Repository Operations (
src/handlers/repository-handlers.ts)- Projects, branches, merge requests, issues
- File operations and branch comparisons
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.
- 3d ago First seen · 511 lines · 4,273 tokens per session scan A 655ed806da6f
mcp-gitlab CLAUDE.md is an instructions file published in the GitHub repository atla-digital/mcp-gitlab (0 stars, last pushed 11mo ago), licensed MIT. It adds 4,273 tokens to every session, about $0.0214 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It comes from a forked repository.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.