GitHub Copilot CLI

AI-powered coding assistant in the terminal. Uses the same agentic engine as GitHub's Copilot coding agent.

Official docs

Install

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

# macOS & Linux
$ curl -fsSL https://gh.io/copilot-install | bash

# Homebrew
$ brew install copilot-cli

# npm
$ npm install -g @github/copilot

# Windows (WinGet)
$ winget install GitHub.Copilot

Install a specific version to a custom path:

1

$ curl -fsSL https://gh.io/copilot-install | VERSION="v0.0.369" PREFIX="$HOME/custom" bash

Launch & authenticate

1

$ copilot

On first launch, use /login to authenticate with GitHub. You need an active Copilot subscription.

You can also authenticate via a fine-grained PAT with the "Copilot Requests" permission, exported as GH_TOKEN or GITHUB_TOKEN.

Keyboard shortcuts

Slash commands

Session

Code & GitHub

Config

Plan mode

Plan mode lets you structure an implementation before writing any code. Models achieve higher success rates when following a concrete plan.

Activate plan mode

• Shift+Tab to toggle between normal mode and plan mode
• Or use /plan directly from normal mode:

1

/plan Add OAuth2 authentication with Google and GitHub providers

What happens

1. Copilot analyzes the request and the codebase
2. Asks clarifying questions to align on requirements
3. Creates a structured plan with checkboxes in plan.md
4. Waits for your approval before implementing

You can edit the plan with Ctrl+Y before starting implementation.

Recommended workflow

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

# 1. Explore the existing code (read-only)
Read the authentication files but don't write code yet

# 2. Plan
/plan Implement password reset flow

# 3. Review and adjust the plan, then implement
Proceed with the plan

# 4. Verify
Run the tests and fix any failures

# 5. Commit
Commit these changes with a descriptive message

When to use /plan

Fleet mode

Fleet mode lets Copilot break a complex task into subtasks executed in parallel by subagents. Each subagent has its own context window.

Usage

Prefix your prompt with /fleet:

1

/fleet Refactor all API endpoints to use the new middleware, add tests for each

How it works

1. The main agent analyzes the prompt and identifies independent subtasks
2. It orchestrates subagents, each working on its part in parallel
3. Results are gathered once all subagents are done

When to use /fleet

Combining with plan + autopilot

The most powerful workflow for large tasks:

1. Shift+Tab → plan mode, create the implementation plan
2. Notice the plan has parallelizable elements
3. Select Accept plan and build on autopilot + /fleet

Choose model per subtask

By default subagents use a lightweight model. You can specify a model in the prompt:

1
2
3

/fleet Use Claude Opus 4.5 to analyze the auth module.
Use GPT-5.3-Codex to generate the migration scripts.
Use @test-writer to create unit tests.

Custom instructions

Copilot reads instructions from these files (in order):

• CLAUDE.md, GEMINI.md, AGENTS.md (in git root & cwd)
• .github/instructions/**/*.instructions.md
• .github/copilot-instructions.md
• $HOME/.copilot/copilot-instructions.md

MCP servers

Copilot ships with GitHub's MCP server by default. Add custom MCP servers via /mcp or by editing the config directly.

LSP support

Copilot CLI supports Language Server Protocol for code intelligence (go-to-definition, hover, diagnostics). Servers are not bundled — install them separately.

Config at user level (~/.copilot/lsp-config.json) or repo level (.github/lsp.json). For instance for Python:

1

$ pip install python-lsp-server

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

{
  "lspServers": {
    "python": {
      "command": "pylsp",
      "args": [],
      "fileExtensions": {
        ".py": "python"
      }
    }
  }
}

Chronicle

The /chronicle slash command leverages your local session history (stored in ~/.copilot/session-state/ and indexed in a SQLite session store) to generate insights about your work.

Subcommands

/chronicle standup

Generates a short report grouped by completion status, based on branches worked on, accomplishments, and linked PRs/issues. Defaults to the last 24 hours.

1
2

/chronicle standup
/chronicle standup for the last 3 days

Example output:

1
2
3
4
5
6
7
8
9

Standup for March 13 2026:

✅ Done
  myapp-repo repo maintenance (main branch)
   - Synced local, cleaned files, audited deps, reviewed architecture

🚧 In Progress
  MyApp configuration (suppress-start-message branch)
   - Suppressing startup init prompt message

/chronicle tips

Analyzes your recent sessions — prompts, tools used, features you haven't tried — and provides 3–5 personalized recommendations. You can focus on a specific area:

1
2

/chronicle tips
/chronicle tips for better prompting

/chronicle improve

Deep-dives into your session history to find friction signals: repeated test failures, build errors, back-and-forth corrections. Generates targeted suggestions for your .github/copilot-instructions.md file.

1

/chronicle improve

After presenting recommendations, Copilot lets you toggle which ones to apply (arrow keys + space), then creates or updates the instructions file.

Asking free-form questions

You don't need /chronicle for every history query. Copilot automatically searches the session store when you ask about past work:

1
2
3

Using what you know about my sessions, what type of tasks give me one-shot successes?
Based on my previous CLI sessions, how could I prompt you in a way that would cost less?
Have I worked on anything related to the payments API?

Session data privacy

All session data stays on your local machine in ~/.copilot/session-state/. Nothing is uploaded beyond normal AI model interactions. Delete a session by removing its directory, then run /chronicle reindex.

Update

1
2
3

$ copilot
# then
/update