GitHub Agentic Workflows Quickstart | GitHub Agentic Workflows
Skip to main content GitHub Agentic Workflows Quickstart Adding an Automated Daily Status Workflow to Your Repo Section titled “Adding an Automated Daily Status Workflow to Your Repo” GitHub Agentic Workflows lets developers define AI-powered repository automation in Markdown with YAML frontmatter (the configuration block between the --- markers at the top of the file) and run AI agents through GitHub Actions. By the end of this guide, you will have a recurring agentic workflow running in your repository with GitHub Copilot, Claude Code, OpenAI Codex, Google Gemini, or Pi.
This guide takes about 10 minutes and requires only the GitHub CLI. Estimated time: 10 minutes In this guide you will add an existing workflow to a GitHub repository where you are a maintainer: the automated Daily Repo Status Report , running in GitHub Actions. Your browser doesn't support HTML5 video. Download Install the extension, add a workflow, and trigger a run from the CLI . Install the extension, add a workflow, and trigger a run from the CLI The aim here is to become familiar with automated AI : to install something that will run automatically , recurrently , in the context of your repository.
Prerequisites Section titled “Prerequisites” Before installing, ensure you have: AI Account - GitHub Copilot , Anthropic Claude , OpenAI Codex , or Google Gemini . Pi uses your Copilot, Anthropic, or OpenAI account, depending on the provider prefix in model: . If you already have GitHub Copilot, start there — it requires no extra account setup. GitHub Repository - A repository where you have write access GitHub Actions enabled - Check in Settings → Actions GitHub CLI ( gh ) v2.0.0+ - Install here .
Check version: gh --version Logged in to GitHub CLI - Verify with gh auth status and run gh auth login --scopes repo,workflow if needed Operating System : Linux, macOS, or Windows with WSL Step 1 - Install the extension Section titled “Step 1 - Install the extension” Install the GitHub Agentic Workflows extension: gh extension install github/gh-aw Step 2 - Add the sample workflow and trigger a run Section titled “Step 2 - Add the sample workflow and trigger a run” Before enabling the workflow, review the selected AI engine’s data handling and setup requirements , repository sensitivity, permitted integrations, and access to logs and artifacts.
From your repository root, run this command: gh aw add-wizard githubnext/agentics/repo-status add-wizard accepts workflow references in <owner>/<repo>/<workflow-name> format. In this guide, githubnext/agentics is the public githubnext/agentics examples repository, and repo-status is one of the sample workflows it publishes. repo-status gathers recent repository activity (issues, PRs, discussions, releases and code changes) and opens a GitHub issue summarizing that activity, community highlights and suggested next steps. description : | This workflow creates daily repo status reports.
It gathers recent repository activity (issues, PRs, discussions, releases, code changes) and generates engaging GitHub issues with productivity insights, community highlights, and project recommendations. See the full source at workflows/repo-status.md . This will take you through an interactive process to: Check prerequisites - Verify repository permissions. Select an AI engine - Choose GitHub Copilot, Claude Code, OpenAI Codex, Google Gemini, or Pi.
Configure AI engine authentication - Follow the instructions or see below. Add the workflow - Adds the workflow file ( .md ) and its generated GitHub Actions lock file to .github/workflows/ , either by direct push or a pull request. Optionally add skills for agentic authoring and debugging - Adds additional files for interactive authoring and debugging of agentic workflows. Optionally trigger an initial run - Starts the workflow immediately.
Configuring authentication Section titled “Configuring authentication” Copilot Use organization billing: If organization billing is enabled in your organization, you can choose Use copilot-requests in the wizard. It adds copilot-requests: write to the workflow permissions and uses the per-run GitHub Actions token for inference. This path requires an organization Copilot subscription with centralized billing. Use COPILOT_GITHUB_TOKEN : Create a fine-grained Personal Access Token (PAT) under your user account.
Under Permissions → Account permissions , set Copilot Requests to Read , then generate the token. Add it as a repository secret from your repository root with gh secret set COPILOT_GITHUB_TOKEN < /path/to/token.txt , or use the GitHub UI. See Copilot authentication for both paths. Claude Setting up ANTHROPIC_API_KEY : Create an API key in Anthropic Console . Add it as a repository secret from your repository root with gh secret set ANTHROPIC_API_KEY < /path/to/key.txt , or use the GitHub UI.
See Authentication for more detail. For keyless authentication, configure Anthropic Workload Identity Federation with a federation rule in your Anthropic workspace and grant the workflow id-token: write . GitHub Actions exchanges a short-lived OIDC token for Anthropic credentials, so you don’t need a repository secret. A Claude subscription token from claude login ( CLAUDE_CODE_OAUTH_TOKEN ) is not supported. The CLI detects it and fails with an error naming CLAUDE_CODE_OAUTH_TOKEN and pointing to ANTHROPIC_API_KEY or Anthropic WIF as the supported alternatives.
Follow Using Claude Code with GitHub Agentic Workflows for the complete setup. Codex Setting up OPENAI_API_KEY : Create an API key in OpenAI API keys . Add it as a repository secret from your repository root with gh secret set OPENAI_API_KEY < /path/to/key.txt , or use the GitHub UI. See Authentication for more detail. Tip: CODEX_API_KEY is also accepted and takes precedence over OPENAI_API_KEY — if you have already stored the key under that name, no action is needed.
See Authentication for details. Gemini Setting up GEMINI_API_KEY : Create an API key in Google AI Studio . Add it as a repository secret from your repository root with gh secret set GEMINI_API_KEY < /path/to/key.txt , or use the GitHub UI. See Authentication for more detail. For keyless authentication, configure Google Workload Identity Federation with a Google Cloud Workload Identity Pool and Provider for GitHub Actions, and grant the service account Vertex AI User permissions.
GitHub Actions exchanges a short-lived OIDC token for Google Cloud credentials, so you don’t need a repository secret. Pi Pi chooses authentication from the provider prefix in model: . It uses Copilot authentication by default, ANTHROPIC_API_KEY for anthropic/... , and CODEX_API_KEY or OPENAI_API_KEY for openai/... and codex/... . For example, use model: copilot/gpt-5.4 , model: anthropic/claude-sonnet-5 , or model: openai/gpt-5 .
Pi also requires tools.github.mode: gh-proxy and tools.cli-proxy: true . Follow Using Pi with GitHub Agentic Workflows for the complete setup. Step 3 - Wait for the workflow to complete Section titled “Step 3 - Wait for the workflow to complete” An automated workflow run can take 2-3 minutes. To watch the run while it’s in flight: From the browser : open the Actions tab of your repository and select the most recent workflow run.
From the CLI : run gh aw status to list workflow state, or gh run watch to stream the latest run. When the run succeeds, a new issue titled with “Daily Repo Report” appears in the Issues tab of your repository. If the run fails, open the run from the Actions tab to view step logs and error output. Once your initial run is complete, a new issue will be created in your repository with a “Daily Repo Report”. The report will be automatically generated and will analyze: Recent repository activity (issues, PRs, discussions, releases, code changes) Progress tracking, goal reminders and highlights Project status and recommendations Actionable next steps for maintainers The report will look something like th
The rest of this page is on the live site.