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/wadew/gitlab-mcp/claude-mdgit clone --depth 1 https://github.com/wadew/gitlab-mcpWhat 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 | $0.02635 | $0.02635 |
| Opus 5 | $0.01318 | $0.01318 |
| Sonnet 5 | $0.00527 | $0.00527 |
| Haiku 4.5 | $0.00264 | $0.00264 |
Grade C, and why
gitlab-mcp CLAUDE.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 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.
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 -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Development Guide - GitLab MCP Server
Ground Rules
Test-Driven Development (TDD) - MANDATORY
ALWAYS write tests first. Watch them fail. Then build code to pass them.
- Red: Write a failing test that defines desired behavior
- Green: Write minimal code to make the test pass
- Refactor: Improve code while keeping tests green
No exceptions. No shortcuts. No "I'll add tests later."
Code Coverage Requirements
- Minimum: 80% code coverage per phase
- Target: 100% test pass rate
- Gate: Cannot proceed to next phase without meeting both criteria
Phase Gate Criteria
Before moving to next phase, ALL must be true:
- ✅ All phase tests written (TDD process followed)
- ✅ 100% of tests passing (no failures, no skips)
- ✅ ≥80% code coverage for phase code
- ✅ Phase documentation complete
- ✅ Session logs updated
- ✅
next_session_plan.mdupdated
Session Management Protocol
CRITICAL: Always maintain continuity between sessions.
Starting a Session (After Context Reset)
- Read this file (
CLAUDE.md) for ground rules - Read
docs/gitlab-mcp-server-prd.mdfor product requirements and feature specs - Read
next_session_plan.mdfor current state and next steps - Review current phase documentation
- Check test coverage and status
During Session
- Follow TDD rigorously
- Update documentation as you go
- Track decisions and issues
- Run tests frequently
Ending a Session (MANDATORY BEFORE CONTEXT RESET)
- Archive current session to
docs/session_management/sessions/ - Update
docs/session_management/session_index.md - MOST CRITICAL: Update
next_session_plan.mdwith:- Current phase and exact progress
- What was completed this session
- Current test coverage numbers
- Any blockers or issues
- Specific next steps (file names, function names, line numbers)
- Ensure all tests are passing
- Commit if at stable checkpoint
Documentation Requirements
Code Documentation
- Docstrings: Every module, class, and function
- Type Hints: All function signatures
- Inline Comments: For complex logic only
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 · 376 lines · 2,635 tokens per session scan C 53ef2f343dbf
gitlab-mcp CLAUDE.md is an instructions file published in the GitHub repository wadew/gitlab-mcp (5 stars, last pushed 7mo ago), licensed MIT. It adds 2,635 tokens to every session, about $0.0132 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
claude-code-config-switcher CLAUDE.md
Instructions for guyskk/claude-code-config-switcher, covering 项目背景, 开发流程, 特别说明：你要使用中文, write idiomatic go code and 提交前检查.
prompts AGENTS.md
Instructions for Sumatoshi-tech/prompts, covering promptkit — golang coding agent personality, working loop, micro-tdd development flow, e2e testing philosophy and architecture preferences.
copilot-tdd-harness tdd-patterns.instructions.md
Go-specific TDD conventions for this repository, including test naming, commands, and test-double guidance.
no-mistakes AGENTS.md
AGENTS.md instructions for kunchenguid/no-mistakes, covering agents.md and maintaining this file.
trpc-agent-go AGENTS.md
AGENTS.md instructions for trpc-group/trpc-agent-go, covering agents.md, project overview, engineering principles, go design conventions and implementation workflow.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.