GitHub Agentic Workflows is a GitHub CLI extension that lets developers define AI-assisted repository automation in Markdown and run it through GitHub Actions. It is intended for tasks requiring interpretation or reasoning, such as issue triage, pull-request review, CI investigation, documentation maintenance, and dependency analysis. The catalogue entries provide skills and agents for working with these workflows.
Borrowing it
Nothing to install: this file belongs to github/gh-aw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/github/gh-aw/main/AGENTS.mdgit clone --depth 1 https://github.com/github/gh-awWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/github/gh-aw/agents-md)<a href="https://agentmods.dev/instructions/github/gh-aw/agents-md"><img src="https://agentmods.dev/badge/instructions/github/gh-aw/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/github/gh-aw/agents-md"><img src="https://agentmods.dev/badge/instructions/github/gh-aw/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02215 | $0.02215 |
| Opus 5.5 | $0.00886 | $0.00886 |
| Sonnet 5.5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
gh-aw AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Agentic Workflows (gh-aw)
GitHub Agentic Workflows (gh-aw) is a GitHub CLI extension that compiles markdown workflows into GitHub Actions.
Important Note: gh-aw vs GitHub Copilot CLI
- gh-aw is the
gh awCLI extension. - copilot is a separate CLI used as one possible runtime engine.
- Use
gh awcommands for workflow authoring/compilation (gh aw compile,gh aw run,gh aw audit).
Ambient Context (First Invocation)
To keep first-turn context small, only these repository root instruction files should be considered ambient:
| File | Purpose |
|---|---|
AGENTS.md |
Minimal global operating rules and routing |
SKILL.md |
Short repository capability summary |
Everything else should be loaded lazily through skills only when needed.
Critical Rules (Always Applicable)
- If you changed files, use
report_progressto commit and push. - Before intermediate
report_progresscalls, runmake agent-report-progress-no-test(fast, no tests). Before the finalreport_progress, runmake agent-report-progress(includestest-unit).test-unitis impacted-first by default (~30s target). UseTEST_UNIT_RUN_FULL=1 make test-unitormake test-unit-allwhen full-suite coverage is required.- Run
test-unitonly once per PR — at the final push, not on every intermediate save.
- After Go changes, run
make fmt. - After workflow markdown changes (
.mdunder.github/workflows/), runmake recompile. - Do not add
.lock.ymlfiles to.gitignore. - Copilot cloud agents may dispatch a workflow only when the user explicitly requests a dry-run test and the exact published source and lock revision has passed the review, compilation, and live-execution gates in
.github/aw/debug-agentic-workflow.md. Compile with--dry-runand dispatch that reviewed revision; compilation alone does not start a run, and dispatch alone does not enable dry-run protections. Dry-run suppresses compiler-managed mutations, not arbitrary script effects. Non-dry-run dispatch remains prohibited. On an authorization error, stop and report it; never retry with different credentials, bypass protections, or ask the user to run it manually. - Large-file guard: before reading any file with
github-mcp-server-get_file_contents, check its size. Files larger than 20 KB must be read with targeted tools (grep,glob,bash, orviewwithview_range) instead of full-file reads. See token-optimization.md for the full technique. - Never ask the user to confirm the plan. Always execute the plan.
- Autopilot mode: Never ask for confirmation before taking action. Never prompt the user with "Should I proceed?", "Do you want me to…?", or any equivalent. Always act immediately and autonomously.
- Grading contract: Follow
.github/skills/operational-value-designer/SKILL.md. Built-ins compute over the in-memory unified session in conclusion; customgraders.<distinct-id>.scriptJavaScript and repository-ownedgraders.operational-value.runBash run only in the separate graders job. Bash reads session JSONL from$1/GH_AW_SESSION_FILE, config JSON fromGH_AW_GRADER_CONFIG, and returns legacy metric arrays; detected file writes are rejected. Shell is trusted code, not yet microVM-isolated. Never add user code or steps to conclusion. Adopt workflow semantics and grader acceptance rules together at the same workflow path and commit; corrections are prospective and prior results are never rewritten.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +72 tokens per session 65be9366de0e
- 6d ago Changed · +51 tokens per session 141f18c6835e
- 16d ago Changed · +1 lines · +34 tokens per session 614c0117340f
- 1mo ago Changed · +1 lines · +104 tokens per session 95a1ca6fd533
- 1mo ago First seen · 149 lines · 1,954 tokens per session scan A 040a1f00a853
gh-aw AGENTS.md is an instructions file published in the GitHub repository github/gh-aw (5,469 stars, last pushed today), licensed MIT. It adds 2,215 tokens to every session, about $0.0089 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.