Concepts for GitHub Copilot CLI

Find out about using Copilot from the command line.

Find out about the various ways you can customize Copilot: what they do, and when to use them.

Find out about the different ways to cancel an active Copilot operation, and how to roll back changes made during a session if the result isn't what you expected.

Remote control lets you monitor and steer a Copilot CLI session from GitHub.com or GitHub Mobile, even after you've stepped away from your machine.

Custom agents enhance Copilot with assistance tailored to your needs.

Plugins are installable packages that extend GitHub Copilot CLI with reusable agents, skills, hooks, and integrations.

Enterprise administrators can centrally define plugin policies for Copilot CLI, ensuring consistent plugin availability across their enterprise.

The CLI's autopilot mode lets Copilot CLI work autonomously on a task, carrying out multiple steps until the task is complete.

The /fleet slash command lets Copilot CLI break down a complex request into smaller tasks and run them in parallel, maximizing efficiency and throughput.

The /research slash command turns Copilot into your research assistant, gathering in-depth information and insights on a topic.

Copilot CLI records every session locally. You can resume previous sessions, ask Copilot questions about your interactions with the CLI, and use the /chronicle slash command for useful session-based insights.

The rubber duck agent is a built-in critic that gives Copilot a constructive second opinion on its own plans, code, and tests—using a different AI model from the one driving your session.

LSP servers give Copilot CLI precise code intelligence, enabling it to navigate definitions, find references, and rename symbols accurately across your project.

Understand how Copilot manages conversation context, what happens during long sessions, and how to stay in control of your context window.