agentleFS
Sign inStart free
mapboxmapbox/mcp-server/.github/copilot-instructions.md

mcp-server

Copilot instructions361 starsChanged 19 days agoMITView on GitHub

This document defines responsible use of GitHub Copilot in this repository. Copilot is a productivity tool that must work within our engineering standards. Copilot learns patterns from existing code. This codebase has strong conventions: Let Copilot learn these patterns rather than explicitly re-teaching them. Remember: Copilot is an assistant, not an authority. You own the code you commit.

  • Reads credentials

We split this copilot-instructions.md into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Understand first: - only use code you fully comprehend

    line 10
  2. Distinctive:

    Iterate: - use suggestions as starting points, not final solutions

    line 12
  3. Very specific:

    Environment variables: - ensure secrets use .env files, never committed

    line 18
  4. Distinctive:

    All Copilot code must comply with standards in CLAUDE.md and docs/engineering_standards.md

    line 22
  5. Distinctive:

    If Copilot suggests patterns inconsistent with the codebase, reject and write manually

    line 24
  6. Distinctive:

    Add or update JSDoc comments as you would for hand-written code

    line 29
  7. Distinctive:

    Update README.md or CHANGELOG.md if user-facing changes

    line 30
  8. Distinctive:

    All Copilot code goes through standard PR review process

    line 34
  9. Distinctive:

    Critical business logic: - prefer hand-written code with thorough review

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 3,669 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
copilot-instructions.md

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 .env files, 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

Let Copilot learn these patterns rather than explicitly re-teaching them.

Remember: Copilot is an assistant, not an authority. You own the code you commit.

Download now (ZIP)

  • Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.

    Of the Copilot instructions files we read, the 2,297 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository2 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free