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/adit-999/gitlab-mcp/copilot-instructionsgit clone --depth 1 https://github.com/Adit-999/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 | $0.00903 | $0.00903 |
| Opus 5 | $0.00451 | $0.00451 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
gitlab-mcp copilot-instructions.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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab MCP Project - GitHub Copilot Instructions
Core Principles
- Target Python 3.13 with all code.
- Adhere strictly to PEP8 for styling and PEP585 for type hinting with built-in generics.
- Use double quotes for strings and docstrings as per project ruff configuration.
- Follow 88 character line length limit as defined in project settings.
- Prioritize explicitness over implicitness in all code.
- Follow the Principle of Least Surprise in API and interface design.
- Avoid inline comments - prefer descriptive variable names and function names instead.
Code Structure
- Favor small, focused
@dataclasses over complex or mutable classes. - Limit function arguments to maximum of 7 parameters as configured in pylint settings.
- Enforce a maximum of 30 statements per function per pylint configuration.
- Use typestate and fluent interfaces where appropriate for ergonomic usage.
- Organize imports according to the isort configuration with order: future, standard-library, third-party, first-party, local-folder.
- Combine imports with the same namespace (e.g.,
from package import Class1, Class2).
Type System
- Require specific type annotations throughout, using Python 3.13 features.
- Use pathlib for all file path operations as enforced by the PTH linting rule.
- Use
Protocolclasses for structural typing when interfaces matter more than inheritance. - Prefer Pydantic models (v2.11+) over unstructured containers for data validation.
Documentation
- Follow Google-style docstrings as specified in the pydocstyle convention.
- Document all public functions, classes, and methods with proper docstrings.
- Include type information in docstrings consistent with annotations.
- Mark TODOs with proper format that can be detected by the TD linting rule.
- Place explanatory comments on separate lines before code, never inline with code.
API Design
- Use Pydantic models for all external input and output validation.
- Ensure consistent, structured error responses with clear codes and messages.
- Follow the Model Context Protocol (MCP) standards for server implementation.
- Design clean, resource-oriented APIs following RESTful principles.
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 · 79 lines · 903 tokens per session scan A ccdd635afe07
gitlab-mcp copilot-instructions.md is an instructions file published in the GitHub repository Adit-999/gitlab-mcp (8 stars, last pushed 1y ago), licensed MIT. It adds 903 tokens to every session, about $0.0045 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.
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.