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/mapbox/mcp-server/copilot-instructionsgit clone --depth 1 https://github.com/mapbox/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 | $0.00484 | $0.00484 |
| Opus 5 | $0.00242 | $0.00242 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
mcp-server 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 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Guidelines for Mapbox MCP Server
This document defines responsible use of GitHub Copilot in this repository. Copilot is a productivity tool that must work within our engineering standards.
Core Principles
1. Review, Don't Auto-Accept
- Always review Copilot suggestions before accepting
- Understand first - only use code you fully comprehend
- No blind copy-paste - adapt suggestions to project context
- Iterate - use suggestions as starting points, not final solutions
2. Security First
- Never accept suggestions with hardcoded secrets, tokens, or credentials
- Review carefully any code handling sensitive data
- Environment variables - ensure secrets use
.envfiles, never committed
3. Quality Standards
- All Copilot code must comply with standards in CLAUDE.md and docs/engineering_standards.md
- Pre-commit hooks will enforce linting, formatting, and TypeScript strictness
- If Copilot suggests patterns inconsistent with the codebase, reject and write manually
4. Testing & Documentation
- Include unit tests for all Copilot-generated features or fixes
- Add or update JSDoc comments as you would for hand-written code
- Update README.md or CHANGELOG.md if user-facing changes
5. Collaboration
- All Copilot code goes through standard PR review process
- Mention in PR description if significant portion is Copilot-generated
- Provide feedback if Copilot produces poor/unsafe suggestions
When to Avoid Copilot
- Critical business logic - prefer hand-written code with thorough review
- Security-sensitive code - authentication, authorization, data validation
- Legal/compliance code - licensing, terms of service, privacy policies
- Architecture decisions - let humans make strategic choices
Learning from the Codebase
Copilot learns patterns from existing code. This codebase has strong conventions:
- Dependency injection for testability (see src/tools/)
- HttpPipeline for all HTTP requests (see src/utils/httpPipeline.ts)
- Consistent tool structure extending MapboxApiBasedTool
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 · 58 lines · 484 tokens per session scan A 97d49afe144e
mcp-server copilot-instructions.md is an instructions file published in the GitHub repository mapbox/mcp-server (353 stars, last pushed 5d ago), licensed MIT. It adds 484 tokens to every session, about $0.0024 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.