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/zephyrdeng/mcp-server-gitlab/copilot-instructionsgit clone --depth 1 https://github.com/ZephyrDeng/mcp-server-gitlabWhat 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 | $0.01840 | $0.01840 |
| Opus 5 | $0.00920 | $0.00920 |
| Sonnet 5 | $0.00368 | $0.00368 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade C, and why
mcp-server-gitlab copilot-instructions.md scanned grade C with 2 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 2d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://bun.sh/install | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://bun.sh/install | bash How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-server-gitlab
mcp-server-gitlab is a GitLab MCP (Model Context Protocol) server built with TypeScript, Bun, and the fastmcp framework. It provides GitLab REST API integration tools for managing projects, merge requests, and user tasks through various MCP-compatible clients like Claude Desktop and Smithery.
Always reference these instructions first and fallback to search or bash commands only when you encounter unexpected information that does not match the info here.
Working Effectively
Bootstrap, Build, and Test the Repository:
-
Install Bun runtime (required):
curl -fsSL https://bun.sh/install | bash source ~/.bashrc -
Install dependencies:
bun install- Fresh install: ~20 seconds, subsequent installs: ~0.02 seconds (cached)
- Installs 608+ packages including TypeScript, Jest, fastmcp, and axios
-
Build the project:
bun run build- Takes approximately 2-3 seconds
- NEVER CANCEL - Always wait for completion
- Runs: clean → TypeScript compilation → post-build script (fixes ES module imports)
- Output: Compiled JavaScript in
dist/directory with executable permissions
-
Run tests:
bun test- Takes approximately 0.14 seconds - very fast
- NEVER CANCEL - Always wait for completion
- Requires environment variables to be set (see Environment Setup section)
- 84 tests across 18 files, all unit tests with mocked API calls
Environment Setup (CRITICAL):
Create .env file before running tests or application:
cp .env.example .env
Edit .env with actual values:
GITLAB_TOKEN=glpat-your-actual-token-here
GITLAB_API_URL=https://your-gitlab-instance.com
Optional environment variables:
# User ID mapping to reduce API calls
GITLAB_USER_MAPPING={"username1": 123, "username2": 456}
# Project ID mapping to reduce API calls
GITLAB_PROJECT_MAPPING={"project-name": 1001, "group/project": "group/project"}
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.
- 2d ago First seen · 183 lines · 1,840 tokens per session scan C 871ab5843951
mcp-server-gitlab copilot-instructions.md is an instructions file published in the GitHub repository ZephyrDeng/mcp-server-gitlab (6 stars, last pushed 7mo ago), licensed MIT. It adds 1,840 tokens to every session, about $0.0092 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.