Automating tasks with Copilot CLI and GitHub Actions

Integrate CLI do GitHub Copilot into your GitHub Actions workflows.

Quem pode usar esse recurso?

CLI do GitHub Copilot está disponível em todos os planos de Copilot. Se você receber o Copilot de uma organização, a política CLI do Copilot deverá ser habilitada nas configurações da organização.

Neste artigo

You can run CLI do GitHub Copilot in a GitHub Actions workflow to automate AI-powered tasks as part of your CI/CD process. For example, you can summarize recent repository activity, generate reports, or scaffold project content. CLI do GitHub Copilot runs on the Actions runner like any other CLI tool, so you can install it during a job and invoke it from workflow steps.

Understanding the workflow

You can define a job in a GitHub Actions workflow that: installs CLI do Copilot on the runner, authenticates it, runs it in programmatic mode, and then handles the results. Programmatic mode is designed for scripts and automation and lets you pass a prompt non-interactively.

Workflows can follow this pattern:

  1. Trigger: Start the workflow on a schedule, in response to repository events, or manually.
  2. Setup: Checkout code, set up environment.
  3. Install: Install CLI do GitHub Copilot on the runner.
  4. Authenticate: Ensure the CLI has the necessary permissions to access the repository and make changes.
  5. Run CLI do Copilot: Invoke CLI do Copilot with a prompt describing the task you want to automate.

The following workflow generates a daily summary of repository changes and prints the summary to the workflow logs.

YAML
name: Daily summary
on:
  workflow_dispatch:
  # Daily at 8:25 UTC
  schedule:
    - cron: '25 8 * * *'
permissions:
  contents: read
jobs:
  daily-summary:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v5
        
      - name: Set up Node.js environment
        uses: actions/setup-node@v4

      - name: Install Copilot CLI
        run: npm install -g @github/copilot

      - name: Run Copilot CLI
        env:
          COPILOT_GITHUB_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
        run: |
          TODAY=$(date +%Y-%m-%d)
          copilot -p "Review the git log for this repository and write a bullet point summary of all code changes that were made today ($TODAY). Include a brief description of what was changed."

Trigger

In this example, the workflow runs on a daily schedule and can also be triggered manually.

The workflow_dispatch trigger lets you run the workflow manually from the Actions tab, which is useful when testing changes to your prompt or workflow configuration.

The schedule trigger runs the workflow automatically at a specified time using cron syntax.

YAML
on:
  # Allows manual triggering of this workflow.
  workflow_dispatch:
  # Daily at 8:30 UTC
  schedule:
    - cron: '30 8 * * *'

Setup

Set up the job so CLI do Copilot can access your repository and run on the runner. This allows CLI do Copilot to analyze the repository context, when generating the daily summary.

The permissions block defines the scope granted to the built-in GITHUB_TOKEN. Because this workflow reads repository data and prints a summary to the logs, it requires contents: read.

YAML
permissions:
  contents: read
jobs:
  daily-summary:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v5

Install

Install CLI do Copilot on the runner so your workflow can invoke it as a command. You can install CLI do GitHub Copilot using any supported installation method. For a full list of installation options, see Como instalar a CLI do GitHub Copilot.

In this example, the workflow installs CLI do GitHub Copilot globally with npm.

YAML
- name: Set up Node.js environment
  uses: actions/setup-node@v4

- name: Install Copilot CLI
  run: npm install -g @github/copilot

Authenticate

To authenticate CLI do Copilot in a workflow, create a fine-grained personal access token (PAT) with the Copilot Requests permission. Store the PAT as a repository secret, then pass it to the CLI using an environment variable. For more information on creating a PAT for the CLI, see Authenticating with a personal access token.

CLI do Copilot supports multiple authentication environment variables. In this example, the workflow uses COPILOT_GITHUB_TOKEN, which is specific to CLI do Copilot and avoids confusion for the built-in GITHUB_TOKEN environment variable.

YAML
- name: Run Copilot CLI
  env:
   COPILOT_GITHUB_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}

Run CLI do Copilot

Run CLI do Copilot in programmatic mode when you want to use it in automation. copilot -p PROMPT executes a prompt programmatically and exits when the command completes.

In this workflow, CLI do Copilot references the repository content that is available in the job workspace. The command prints its response to standard output and the summary appears in the workflow logs.

YAML
- name: Run Copilot CLI
  env:
    COPILOT_GITHUB_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
  run: |
    TODAY=$(date +%Y-%m-%d)
    copilot -p "Review the git log for this repository and write a bullet point summary of all code changes that were made today ($TODAY). Include a brief description of what was changed."

Next steps

After you confirm the workflow prints a summary to the logs, you can adapt the same pattern to other automation tasks. Start by changing the prompt you pass to copilot -p PROMPT, then decide what you want to do with the output.

  • Write the summary to a file so later steps can use it as input.
  • Post the summary as a comment on an issue or a message in a team chat.
  • Summarize requests and output a draft changelog.

Further reading