aw-author

A skill for creating and maintaining GitHub Agentic Workflow files. These are Markdown files with settings that are compiled into GitHub Actions, GitHub's service for running automated repository tasks.

In plain words
What is it for?
Use it to create a workflow, generate one from a description, validate its settings, improve an existing file, or investigate a failing workflow.
Why use it?
It provides a defined path for creating, checking, improving, or debugging these workflows. It also chooses the appropriate process based on the requested job.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/zircote-plugins/github-agentic-workflows/aw-author
Any agent
npx skills add zircote-plugins/github-agentic-workflows --skill aw-author
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/github-agentic-workflows

Made for: Claude Code, Codex.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,941 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00091 $0.04941
Opus 5 $0.00046 $0.02471
Sonnet 5 $0.00018 $0.00988
Haiku 4.5 $0.00009 $0.00494

Measured yesterday against content hash d3c3c0bf875e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aw-author scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

27. **MCP server stdout breaks initialization** — any stdout before the JSON-RPC handshake breaks the MCP gateway; redirect all `apk add`, `pip install`, `curl` output to `/dev/null`
skills/aw-author/SKILL.md · 431 lines

How it starts

The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Agentic Workflow Author

You are an expert in GitHub Agentic Workflows (gh-aw) — a system that uses markdown files with YAML frontmatter to define agentic automation compiled into GitHub Actions via gh aw compile.

Mode Detection

Determine the user's intent and route to the appropriate mode:

User Intent Mode Trigger Phrases
Create a new workflow from scratch Interactive "new", "create", "write", "build"
Generate a workflow from a description Generate "generate", "one-shot", "quick"
Check an existing workflow for errors Validate "validate", "check", "verify", "lint"
Improve an existing workflow Improve "improve", "optimize", "refine", "review"
Debug a failing workflow Debug "debug", "fix", "broken", "failing", "error"
Ask about the spec or features Query Any question about gh-aw capabilities

If the mode is ambiguous, ask the user:

AskUserQuestion: "What would you like to do with your gh-aw workflow?"
Options:
  - "Create new workflow (guided)" → Interactive mode
  - "Generate from description (one-shot)" → Generate mode
  - "Validate existing workflow" → Validate mode
  - "Improve existing workflow" → Improve mode
  - "Debug a failing workflow" → Debug mode

Interactive Mode (Guided Authoring)

Walk the user through building a workflow step by step using AskUserQuestion at each phase.

Phase 1: Purpose & Trigger

AskUserQuestion: "What should this workflow do?"
  → Free text description

AskUserQuestion: "What triggers this workflow?"
Options:
  - "New/updated issues" → on.issues
  - "New/updated pull requests" → on.pull_request
  - "Issue/PR comments (slash commands)" → on.issue_comment
  - "Scheduled (cron/daily)" → on.schedule
  - "Manual dispatch" → on.workflow_dispatch
  - "Push to branch" → on.push
  - "Discussion events" → on.discussion

For event-triggered workflows (issues, PRs, comments, discussions), always include reaction: eyes in the on: block. This grants the compiler permissions for pre_activation.

Read the full file on GitHub · 431 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday First seen · 431 lines · 91 tokens per session scan A d3c3c0bf875e

Subscribe to this mod's changes

aw-author is a skill published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 4,941 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.