Configure this project with agentic workflows

Hey agent! If this repository hasn't been configured with agentic workflows yet, here is how to set it up.

1. Install the gh aw CLI extension using the install script (no GitHub token required):

   curl -sL https://raw.githubusercontent.com/github/gh-aw/main/install-gh-aw.sh | bash

2. Choose an engine, then run the init command to configure the repository. Replace <engine> with copilot, claude, codex, gemini, or pi:

   gh aw init --engine <engine>

3. Add a daily repo status agentic workflow using the add command:

   gh aw add --engine <engine> --create-pull-request

   The workflow should:

   • Run on a daily schedule
   • Summarize the repository status (open issues, recent PRs, CI health)
   • Use the Quick Start engine selector to choose your runtime:
     • For copilot, grant copilot-requests: write
     • For claude, set ANTHROPIC_API_KEY or configure Anthropic WIF. CLAUDE_CODE_OAUTH_TOKEN from claude login is not supported.
     • For codex, set CODEX_API_KEY or OPENAI_API_KEY
     • For gemini, set GEMINI_API_KEY or configure Google WIF
     • For pi, configure provider authentication and the required proxies

GitHub Agentic Workflows

GitHub Agentic Workflows (gh-aw) lets developers define AI-powered repository automation in Markdown with YAML frontmatter and run AI agents securely through GitHub Actions. The gh-aw GitHub CLI extension compiles each agentic workflow into a standard GitHub Actions workflow.

Use conventional GitHub Actions for deterministic builds, tests, linting, deployments, and reproducible scripts. Add an agentic workflow when a task needs reasoning or interpretation, such as issue triage, pull-request review, CI failure investigation, documentation maintenance, dependency analysis, or repository reporting. GitHub Agentic Workflows complements existing CI/CD; it does not replace it.

Built-in AI engines include GitHub Copilot, Claude Code, OpenAI Codex, Google Gemini, and Pi. Agent jobs are read-only and sandboxed by default, and configured GitHub writes are normally applied through validated safe-outputs jobs with scoped permissions.

Note

Releases 0.68.4 through 0.71.3 are being retired due to a bug that impacts billing. If you are running one of these versions, please upgrade to the latest release as soon as possible.

Contents

• Quick Start
• How GitHub Agentic Workflows works
• Security and permissions
• Documentation
• Contributing
• Community Contributions
• Related Projects
• Workshop

Quick Start

Install the GitHub CLI extension:

gh extension install github/gh-aw

Then follow the GitHub Agentic Workflows quickstart to select an AI engine, add a sample workflow, and run it through GitHub Actions.

How GitHub Agentic Workflows works

An agentic workflow has two parts: YAML frontmatter configures triggers, permissions, tools, and the AI engine; the Markdown body tells the AI agent what to accomplish. The gh aw compile command validates this source and generates the .lock.yml workflow that GitHub Actions executes. Learn how GitHub Agentic Workflows works.

Security and permissions

Security, permissions, and controlled writes are core design concerns. The supported agent-job path defaults to read-only GitHub access and sandboxed execution. Safe outputs buffer configured writes, validate them, and apply them in separate jobs with scoped permissions. These controls are configurable, so workflow authors must review permissions, tools, network access, and generated files before deployment. Learn how GitHub Agentic Workflows handles security and permissions.

Using agentic workflows in your repository requires careful attention to security considerations and careful human supervision, and even then things can still go wrong. Use it with caution, and at your own risk.

Documentation

Use the GitHub Agentic Workflows documentation for these paths:

• Create an agentic workflow
• Choose and authenticate an AI engine
• Browse GitHub Agentic Workflows examples by task
• Review the security architecture
• Read the GitHub Agentic Workflows FAQ

For AI agents and retrieval tools, use the published agent prompt index, full prompt corpus, and AI-readable project summary.

Contributing

For development setup and contribution guidelines, see CONTRIBUTING.md.

Custom Go linters

To build and test repository custom linters:

• go test ./pkg/linters/<linter-name>/...
• go build ./cmd/linters
• make golint-custom

make golint-custom builds cmd/linters and runs the custom analyzers against ./cmd/... and ./pkg/....

🌍 Community Contributions

^{Community members whose issues were resolved — updated automatically.}

@aaronspindler (1) @abillingsley (2) @adam-cobb (1) @adamhenson (2) @adamtasteslikegood (1) @adhikjoshi (1) @ahmadabdalla (1) @ajfeldman6 (1) @AkshatRaj00 (1) @alanpeabody (1) @alcastaneda (1) @AlexanderWert (1) @AlexDeMichieli (1) @alexsiilvaa (2) @alondahari (17) @alvistar (2) @AmoebaChant (1) @anthonymastreanvae (10) @aoxiangtianyu-go (1) @apenab (1) @arabkin (1) @arezero (6) @arthurfvives (8) @Artur- (1) @askpaisa (1) @askpt (1) @astefan (1) @awoisoak (1) @b2pacific (1) @babaakihiro (2) @bartul (1) @bbonafed (23) @beardofedu (1) @benissimo (7) @benvillalobos (12) @blozano-tt (7) @bmerkle (3) @boydj (2) @Bra1nFartz (1) @BrandonLewis (1) @bryanchen-d (22) @bryanknox (1) @bshore-bf (1) @Calidus (7) @camposbrunocampos (2) @carlincherry (1) @carlosflorencio (1) @CatsMiaow (1) @chepa92 (1) @chrisfregly (2) @chrizbo (7) @CiscoRob (2) @cknight (2) @clementbolin (1) @cogni-ai-ee (2) @consulthys (3) @Corb3nik (3) @corygehr (20) @corymhall (1) @crmitchelmore (1) @dagecko (1) @Daidanny008 (1) @Dan-Albrecht (1) @Dan-Co (2) @danielmeppiel (6) @danquirk (1) @darwin-gonzales (1) @davidahmann (3) @davidslater (1) @dbudym-cs (1) @DeagleGross (2) @devantler (2) @deyaaeldeen (10) @dfrysinger (2) @dgolombek (1) @dholmes (3) @dhrapson (2) @DimaBir (1) @dkurepa (1) @DogeAmazed (1) @doughgle (1) @drehelis (4) @DrPye (1) @dsfaccini (1) @dsibilio (3) @dsolteszopyn (2) @dsyme (33) @duncankmckinnon (1) @eaftan (3) @edburns (1) @edgeq (2) @elika56 (1) @emexelem (1) @enbw-mmattes (1) @eran-medan (1) @ericchansen (1) @ericstj (2) @Esomoire-consultancy-Company (1) @Etienne-M (1) @Evangelink (5) @fbecar22 (2) @FDevTakima (1) @ferryhinardi (1) @flatiron32 (2) @florianbader (1) @fr4nc1sc0-r4m0n (1) @funkymonkeyjam (2) @G1Vh (1) @GandrotulaRajesh (1) @github-actions (10) @github-antoine-brechon (4) @GKersten (1) @glitch-ux (1) @grahame-white (9) @graphaelli (1) @GregoireW (1) @h-no (1) @h3y6e (2) @haavamoa (1) @haolpku (1) @harrisoncramer (2) @heaversm (1) @heiskr (6) @hermanho (1) @holwerda (3) @hpsin (1) @hrishikeshathalye (1) @ianreay (1) @IEvangelist (14) @Infinnerty (1) @insop (1) @ivancea (9) @j-srodka (6) @jamesadevine (4) @JamesNK (4) @JanKrivanek (4) @jaroslawgajewski (26) @JasonYeMSFT (1) @jbaruch (1) @jcooklin (1) @jeffhandley (12) @jeremiah-snee-openx (1) @jfomhover (1) @jhamon (2) @jitran (4) @joesturge (1) @johnpreed (5) @johnwilliams-12 (11) @jonathanpeppers (4) @joperezr (1) @JoshGreenslade (2) @jsalmassy (1) @jsoref (2) @jsquire (1) @jtracey93 (1) @kaovilai (4) @karl-petter-sj (1) @katriendg (1) @kbreit-insight (5) @KGoovaer (1) @kkruel8100 (1) @Krzysztof-Cieslak (1) @kthompson (1) @labudis (2) @ladamski (1) @lecoursen (1) @lilseyi (2) @lindeberg (1) @loganrosen (4) @look (1) @lpcox (6) @ludoviclafole (1) @lukeed (1) @lupinthe14th (3) @m-titov (1) @maikelvdh (2) @mark-hingston (1) @mason-tim (8) @matiloti (4) @mattcosta7 (1) @MatthewBunker (2) @MatthewLabasan-NBCU (2) @MattSkala (3) @MauroDruwel (4) @maxbeizer (1) @maxknv (1) @mcantrell (1) @mdashrraf (1) @MH0386 (1) @mhavelock (1) @michen00 (2) @microsasa (9) @mlinksva (1) @mnkiefer (5) @molson504x (2) @Mossaka (3) @mrfelton (5) @mrjf (7) @MrSanchez (1) @mstrathman (1) @mvdbos (2) @nestele (2) @neta-vega (3) @NicoAvanzDev (3) @NicolasRannou (1) @nihal467 (1) @Nikhil-Anand-DSG (1) @NikolajBjorner (2) @norrietaylor (8) @not-mksv (1) @octatone (1) @oscarvalenzuelab (1) @PaulAylward2 (1) @petercort (1) @pethers (1) @pgaskin (1) @pholleran (4) @Phonesis (1) @Pierrci (1) @plengauer (1) @pmalarme (1) @polmichel (2) @ppusateri (1) @praveenkuttappan (1) @PureWeen (9) @qwert666 (1) @r-garcia-de-oliveira (2) @rabo-unumed (4) @racedale (1) @radiantspace (2) @rafael-unloan (1) @rbstp (2) @reggie-k (3) @rhardouin (2) @rmarinho (1) @romainh-betclic (3) @rspurgeon (4) @Rubyj (3) @ruokun-niu (1) @ryckmansm (2) @salekseev (3) @salmanmkc (1) @samuelkahessay (30) @samus-aran (1) @SanthoshNandha (1) @sbodapati-gfm (1) @seangibeault (2) @seesharprun (4) @sg650 (13) @shawnHartsell (1) @shiran-gutsy (1) @shubhamtanwar23 (3) @siyo-rms (1) @srgibbs99 (6) @ssulei7 (1) @stacktick (1) @stefankrzyz (1) @steliosfran (3) @straub (6) @strawgate (45) @susmahad (3) @swimmesberger (1) @syarihu (1) @szabta89 (3) @tadelesh (1) @Tarekchehahde (2) @theletterf (17) @thi-feonir (1) @timdittler (3) @tinytelly (1) @tobio (1) @tomasmed (1) @tore-unumed (16) @trask (4) @tsm-harmoney (5) @tspascoal (2) @tvu4-wowcorp (1) @tylersmalley (1) @UncleBats (2) @v1v (4) @verkyyi (2) @veverkap (3) @ViktorHofer (3) @virenpepper (1) @vishalagrawal-jisr (2) @whoschek (1) @wizardofosmium (1) @wtgodbe (4) @xirzec (1) @yaananth (1) @Yoyokrazy (2) @yskopets (53) @zarenner (5) @zkoppert (2)

Related Projects

GitHub Agentic Workflows is supported by companion projects that provide additional security and integration capabilities:

• Agent Workflow Firewall (AWF) - Network egress control for AI agents, providing domain-based access controls and activity logging for secure workflow execution
• MCP Gateway - Routes Model Context Protocol (MCP) server calls through a unified HTTP gateway for centralized access management
• gh-aw-actions - Shared library of custom GitHub Actions used by compiled workflows, providing functionality such as MCP server file management

Workshop

Tip

Ready to learn GitHub Agentic Workflows hands-on? The Factory Tour Workshop is a self-contained, step-by-step workshop repository designed to teach you how to build, run, and customize agentic workflows from scratch.