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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add github/gh-aw --skill review-agentic-workflowsgit 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/skills/github/gh-aw/review-agentic-workflows)<a href="https://agentmods.dev/skills/github/gh-aw/review-agentic-workflows"><img src="https://agentmods.dev/badge/skills/github/gh-aw/review-agentic-workflows/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/skills/github/gh-aw/review-agentic-workflows"><img src="https://agentmods.dev/badge/skills/github/gh-aw/review-agentic-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 9 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00029 | $0.01670 |
| Opus 5.5 | $0.00012 | $0.00668 |
| Sonnet 5.5 | $0.00006 | $0.00334 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
review-agentic-workflows 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 15d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Agentic Workflows
Use this skill when asked to review .github/workflows/*.md agentic workflows or their generated .lock.yml outputs.
Reference workflow authoring skill guidance at: https://raw.githubusercontent.com/github/gh-aw/main/.github/skills/agentic-workflows/SKILL.md
Goals
- Produce a security-first review of workflow changes.
- Compile workflows with validation and security scanners.
- Flag suspicious changes that weaken protections.
- Use run history (
logs/audit) when available to find optimization opportunities.
Agent ownership
The agent performs setup, source and runtime-dependency inspection, independent single-reviewer coordination, compilation/scanners, evidence collection, finding resolution and cleanup. Do not give the user a technical preflight checklist to execute. Report concrete blockers and request only authorization or decisions the agent cannot supply. For debugging and live-test gates, follow the shared security-review guidance; the agent prepares the evidence for human validation rather than asking the user to conduct the review.
Require exactly one read-only security-review agent per reviewed revision. Resolve coverage questions with that reviewer; do not require parallel judges, majority votes or a tie-breaker. Follow the shared single-reviewer rules.
The user may explicitly authorize live debugging for the current session rather than approve each run. Record the grant and agreed scope/bounds; reuse it for in-scope revisions only after the agent repeats the required technical review. Any compiler security warning invalidates session approval immediately, even if later fixed: resolve it, re-review, and obtain fresh explicit authorization. Follow the shared session authorization rules; a request to update this skill is not itself a session-wide execution grant.
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.
- 15d ago Changed 7d0367ea9d62
- 26d ago Changed · +12 lines a4f4a6f4da12
- 29d ago Changed · +45 lines e74c5933f17f
- 2mo ago First seen · 125 lines · 29 tokens per session scan A 905d53765e01
review-agentic-workflows is a skill published in the GitHub repository github/gh-aw (5,579 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,670 once invoked, about $0.0001 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 2026-08-30.
review-agentic-workflows compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-agentic-workflowsgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 29 | Claude Code, Codex |
| watch-prjustincampbell/gh-watch | Skill | 4 | 7d ago | MIT | A | 48 | Claude Code |
| ci-cdLuuOW/meridian-mcp | Skill | 0 | 24d ago | MIT | C | 48 | Claude Code, Codex |
| deployjeremylongshore/tons-of-skills-marketplace | Skill | 2.9k | yesterday | MIT | A | 76 | Claude Code |
| code-review-githubinitializ/forge | Skill | 235 | yesterday | Apache-2.0 | A | 30 | Claude Code, Codex |
| release-habit-hookshabit-hooks/habit-hooks | Skill | 250 | 1mo ago | MIT | A | 56 | Claude Code, Codex |
| habit-hooks-reviewhabit-hooks/habit-hooks | Skill | 250 | 1mo ago | MIT | A | 51 | Claude Code, Codex |