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/jmrplens/gitlab-mcp-server/context-engineeringgit clone --depth 1 https://github.com/jmrplens/gitlab-mcp-serverWhat 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 | $0.00545 | $0.00545 |
| Opus 5 | $0.00272 | $0.00272 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
gitlab-mcp-server context-engineering.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 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.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Engineering
Principles for helping GitHub Copilot understand your codebase and provide better suggestions.
Project Structure
- Use descriptive file paths:
src/auth/middleware.ts>src/utils/m.ts. Copilot uses paths to infer intent. - Colocate related code: Keep components, tests, types, and hooks together. One search pattern should find everything related.
- Export public APIs from index files: What's exported is the contract; what's not is internal. This helps Copilot understand boundaries.
Code Patterns
- Prefer explicit types over inference: Type annotations are context.
function getUser(id: string): Promise<User>tells Copilot more thanfunction getUser(id). - Use semantic names:
activeAdultUsers>x. Self-documenting code is AI-readable code. - Define constants:
MAX_RETRY_ATTEMPTS = 3> magic number3. Named values carry meaning.
Working with Copilot
- Keep relevant files open in tabs: Copilot uses open tabs as context signals. Working on auth? Open auth-related files.
- Position cursor intentionally: Copilot prioritizes code near your cursor. Put cursor where context matters.
- Use Copilot Chat for complex tasks: Inline completions have minimal context. Chat mode sees more files.
Context Hints
- Add a COPILOT.md file: Document architecture decisions, patterns, and conventions Copilot should follow.
- Use strategic comments: At the top of complex modules, briefly describe the flow or purpose.
- Reference patterns explicitly: "Follow the same pattern as
src/api/users.ts" gives Copilot a concrete example.
Multi-File Changes
- Describe scope first: Tell Copilot all files involved before asking for changes. "I need to update the User model, API endpoint, and tests."
- Work incrementally: One file at a time, verifying each change. Don't ask for everything at once.
- Check understanding: Ask "What files would you need to see?" before complex refactors.
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 · 45 lines · 545 tokens per session scan A 303780cee09b
gitlab-mcp-server context-engineering.instructions.md is an instructions file published in the GitHub repository jmrplens/gitlab-mcp-server (31 stars, last pushed 2d ago), licensed MIT. It adds 545 tokens to every session, about $0.0027 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 2026-08-30.
Other instructions, from other repositories
graymatter AGENTS.md
Instructions for angelnicolasc/graymatter, covering agents.md, your tools, when to call which, first call and identity.
graymatter CLAUDE.md
Instructions for angelnicolasc/graymatter, covering claude.md, a user asked you to set graymatter up, you are working in a project that already uses graymatter and you are contributing to graymatter itself.
syllago CLAUDE.md
Instructions for OpenScribbler/syllago, covering syllago, build and test, key conventions, architectural decisions and testing requirements.
mcp-gitlab AGENTS.md
Instructions for vish288/mcp-gitlab, covering mcp-gitlab — agent context, architecture, patterns, mcp compliance rules and tool annotations (mandatory).
the-matrix CLAUDE.md
Instructions for 0merUfuk/the-matrix, covering the-matrix — autonomous agent ecosystem, tool inventory, system topology, data flow and runtime selection.
mcp-gitlab GEMINI.md
Instructions for vish288/mcp-gitlab, covering mcp-gitlab — gemini cli extension context, tool categories, common workflows and notes.