# GitHub Copilot playbooks

GitHub's AI coding assistant. It works in many IDEs, on github.com, in the Copilot CLI, the Copilot desktop app and GitHub Mobile. Developers use agent mode to edit code in the editor, and they assign issues to the cloud agent, which works in the background and opens a pull request.

- Vendor: GitHub
- Kind: coding-agent
- Surfaces: ide, web, terminal, desktop, mobile
- Connects: The IDEs, CLI and Copilot app use local and remote MCP servers. The cloud agent and code review use servers set at the repository level, plus GitHub and Playwright servers by default. Skills live in .github/skills, .claude/skills or ~/.copilot/skills.

- Docs: https://docs.github.com/en/copilot

## Good at

- Assigning a GitHub issue to the cloud agent and getting a pull request to review
- Agent mode in VS Code and other editors that edits files and runs commands
- Reviewing pull requests and suggesting fixes you can apply
- Choosing third-party agents such as Claude and Codex on some plans

## Limits

- The cloud agent uses MCP tools without asking, supports only tools, not resources or prompts, and does not support remote servers that use OAuth
- On Business and Enterprise plans an admin must turn on the cloud agent and MCP first
- Its default Playwright browser can only reach localhost inside its own environment

## Playbooks (5)

- [Map an unfamiliar codebase into a checked architecture document before you change it](https://agentshandbook.com/p/map-an-unfamiliar-codebase-before-you-change-it.md): You have a docs/architecture.md that names the entry points, modules and data flow with file references, a list of open questions, and a short instruction file with the build and test commands.
 (trust: corroborated, risk: low)
- [Test your local web app in a real browser and fix console errors in one loop](https://agentshandbook.com/p/test-local-web-app-in-browser-and-fix-console-errors.md): You get a table of the console errors and failed requests on each route you named, a small fix for each one, and proof from a reload that the error is gone.
 (trust: corroborated, risk: low)
- [Triage a production error from Sentry or logs into a tested fix pull request](https://agentshandbook.com/p/triage-production-error-into-a-fix-pr.md): You get a short root cause note backed by the stack trace and code, a failing test that reproduces the error, a small fix that makes it pass, and a local branch ready for your review.
 (trust: corroborated, risk: medium)
- [Turn small tracker issues into reviewed pull requests with cloud coding agents](https://agentshandbook.com/p/turn-issues-into-pull-requests-with-cloud-agents.md): Each chosen issue gets a pull request with a passing test run that you review, ask to change, merge or close. You stay in control of every merge.
 (trust: corroborated, risk: medium)
- [Upgrade a framework across a repo with a coding agent and the test suite as the gate](https://agentshandbook.com/p/upgrade-a-framework-across-a-repo-with-tests-as-the-gate.md): The repo runs on the new version on a branch of small commits, the full test suite passes with no tests removed, and you have a list of behaviour changes to check in staging.
 (trust: corroborated, risk: medium)

## Lessons

- [Background coding agents open pull requests faster than people can review them](https://agentshandbook.com/lessons/background-agent-prs-overwhelm-reviewers.md)
- [Coding agents write code for old library versions or invent APIs](https://agentshandbook.com/lessons/coding-agents-use-outdated-library-apis.md)
- [Coding agents change, skip or misreport tests to reach a green run](https://agentshandbook.com/lessons/coding-agents-weaken-tests-to-pass.md)