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 docs-designgit 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/docs-design)<a href="https://agentmods.dev/skills/github/gh-aw/docs-design"><img src="https://agentmods.dev/badge/skills/github/gh-aw/docs-design/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/docs-design"><img src="https://agentmods.dev/badge/skills/github/gh-aw/docs-design.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 | $0.00041 | $0.00970 |
| Opus 5.5 | $0.00016 | $0.00388 |
| Sonnet 5.5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
docs-design 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 28d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs site and landing page design rules
The docs site and the landing page (docs/src/content/docs/index.mdx and docs/src/components/landing/) had a deliberate design pass. These rules hold that design in place on both. Each one exists for the reader, and each states its reason so you can explain it.
When a request breaks a rule
Requests like "there's too much white space" or "add X to the header" often point to a real problem with the wrong fix. When a requested visual change breaks a rule below:
- Find the problem the requester actually has (the page feels empty, a feature is hard to find).
- Implement a fix for that problem that stays inside the rules.
- In the PR description, name the rule, give its reason in a sentence or two, and say what you did instead.
A rule changes only when the designer who owns it agrees, and the change updates this file in the same PR.
Reading measure
On docs pages, body content is at most 620px wide (--aw-prose-width in docs/src/styles/custom.css). That includes the page title, prose, lists, asides, tabs, code blocks, the edit/last-updated row and the prev/next pager.
Why: line length decides how easy text is to read. The comfortable range is roughly 45–75 characters per line, and about 66 is ideal. Past that, the eye loses its place on the long sweep back to the start of the next line, rereads lines or skips them, and long pages become tiring. Body text is 16px Mona Sans, a narrow face averaging ~7.3px per character, so 620px holds about 80 characters per line: already at the top of what reads comfortably. Wider columns look fuller on a big monitor and read worse at every size.
- Tables, mermaid diagrams and images may grow wider than 620px when their content needs it. They're scanned, not read line by line, so the measure doesn't apply to them.
- Size the measure in
rem, neverch.1chis the width of the "0" glyph (~10px here), so70chis ~700px, or ~92 real characters. - The landing page lays its sections out in a wider 72rem container, but its running text (intros, descriptions) still stays within a comfortable measure.
- If a wide screen feels empty, that space is the cost of readable text. The column is centred between the sidebar and "On this page" so the space sits evenly on both sides.
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.
- 28d ago First seen · 52 lines · 41 tokens per session scan A 71b702f4101c
docs-design is a skill published in the GitHub repository github/gh-aw (5,579 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 970 once invoked, about $0.0002 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 2026-10-10.
docs-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docs-designgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 41 | Claude Code, Codex |
| Visual Regression ReviewRaidriar7170/hermes-skilleval | Skill | 29 | 1mo ago | MIT | A | 20 | Claude Code, Codex |
| watch-prjustincampbell/gh-watch | Skill | 4 | 7d ago | MIT | A | 48 | Claude Code |
| watch-tagjustincampbell/gh-watch | Skill | 4 | 7d ago | MIT | A | 62 | Claude Code |
| watch-branchjustincampbell/gh-watch | Skill | 4 | 7d ago | MIT | A | 45 | Claude Code |
| watch-commitjustincampbell/gh-watch | Skill | 4 | 7d ago | MIT | A | 48 | Claude Code |
| adobe-photoshopalivirgo/Major-AI-Skills | Skill | 2 | yesterday | MIT | A | 48 | Claude Code |