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/.github/skills/create-canvas/SKILL.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/skills/github/gh-aw/create-canvas)<a href="https://agentmods.dev/skills/github/gh-aw/create-canvas"><img src="https://agentmods.dev/badge/skills/github/gh-aw/create-canvas/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/create-canvas"><img src="https://agentmods.dev/badge/skills/github/gh-aw/create-canvas.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 Rogue Agent · line 189 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00061 | $0.03549 |
| Opus 5.5 | $0.00024 | $0.01420 |
| Sonnet 5.5 | $0.00012 | $0.00710 |
| Haiku 4.5 | $0.00006 | $0.00355 |
Grade A, and why
create-canvas scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extension Canvas Authoring
Use this skill when creating or debugging an extension canvas that integrates with the runtime canvas model.
The host app no longer participates in extension canvas registration. Extensions declare canvases directly to the runtime via the Copilot SDK on joinSession; the runtime routes provider callbacks (canvas.open, canvas.action.invoke, etc.) straight to the declaring connection; the host app just renders whatever URL the provider returns.
Authoring workflow (do this in order)
-
Decide the scope. Project (
.github/extensions/<name>/) is committed to the repo and shared with the team. User ($COPILOT_HOME/extensions/<name>/) is local to the current user. Session ($COPILOT_HOME/session-state/<sessionId>/extensions/<name>/) is loaded only for the current session — ideal for a throwaway canvas for one conversation. Unless the request makes it obvious, ask before creating files — the choice changes who sees the extension, whether it's committed, and the resultingextensionId. -
Scaffold via tool, don't hand-write the skeleton.
extensions_manage({ operation: "scaffold", kind: "canvas", name: "<name>", location: "project" | "user" | "session" })The canvas scaffold produces an
extension.mjswithjoinSession({ canvases: [createCanvas({...})] }), a working loopback HTTP server per instance, an example action, andonClosecleanup. Edit from there. -
Edit the file. Implement your
open,actions[], optionalonClose, and (if needed) tools/hooks alongside. -
Reload. Call
extensions_reload. Stale canvas instances flip tostale, then back toreadyonce the provider reconnects. -
Verify. Call
extensions_manage({ operation: "list" })andextensions_manage({ operation: "inspect", name: "<name>" }). If the extension is marked failed,inspectsurfaces the log file path and a tail — that log is the primary debugging surface. -
Drive it. Run the validation checklist below via
list_canvas_capabilities,open_canvas, andinvoke_canvas_action.
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.
- 1mo ago First seen · 260 lines · 61 tokens per session scan A d8b3307a7d48
create-canvas is a skill published in the GitHub repository github/gh-aw (5,406 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 3,549 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 2026-08-30.
Other skills, from other repositories
c-github
Interact with GitHub using the gh CLI and jq. Manage PRs, issues, repositories, and Actions workflows. Make raw API calls with gh api for anything not covered by built-in commands.
watch-pr
Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.
watch-tag
Watch a GitHub repository for new tags using the gh-watch extension. Use when the user wants to be notified when a tag is created, when a release is cut, or when a tag that includes a specific commit appears (e.g. "tell me when my merge ships in a release").
watch-branch
Watch a GitHub branch for new commits using the gh-watch extension. Use when the user wants to be notified when new commits are pushed to a branch, monitor main for merges, or track branch activity.
watch-commit
Watch a GitHub commit for CI status changes using the gh-watch extension. Use when the user wants to monitor a commit's CI checks, wait for a build to finish, or track CI progress on a specific SHA.
update-architecture-docs
Generate or update the architecture documentation in docs/content/architecture/. Use on "update architecture docs", "generate architecture documentation", "regenerate architecture docs", or after any structural change to the codebase.