Skip to content
TraeIDE

Search

Popular pages

No matching pages

Try a tool name or a topic such as pricing or MCP.

English

GitHub Copilot CLI Guide

GitHub’s terminal coding agent with repository context and Copilot account access.

Last verified: · How we verify
Coding agentGitHubmacOSWindowsLinux

Suitable workflows

Developers who combine terminal work with GitHub repositories and code review.

Limitations and billing

Organization administrators must enable CLI access; allowances follow the Copilot plan.

Capabilities we verified

Agent workflowCLI surfaceMCP

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

Pricing & usage

Free access; see limits

Copilot plan and its usage allowance. The cost of metered usage or an external agent can be separate from the subscription.

Check official pricing ↗

Models & access

Select from the models enabled for your Copilot account and organization.

Verified families: Claude, GPT.

Official model information ↗

Install and start the CLI

Node.js 22+ for npm; official Homebrew and Windows WinGet options are also available.

Installation command · npm

npm install -g @github/copilot

Open your project folder in a terminal, then run:

copilot
Official installation instructions ↗

Account and authentication

Start copilot, run /login and approve access with your GitHub account.

Project configuration and tools

Inspect trusted folders and tool approvals. Add MCP servers through /mcp or copilot mcp add.

First task to try

Review a local change and identify which tests should run before opening a pull request.

Official configuration reference ↗

Related CLI tools

All AI CLI tools →

Project evaluation checklist

  1. Open a small, familiar project and confirm that your essential language tooling works.
  2. Give the agent one bounded change with an observable acceptance criterion.
  3. Review the diff, run the project’s checks and compare the result with your current workflow.
  4. Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.