aw-author

A command for creating, checking, improving, and troubleshooting GitHub Agentic Workflow files, which describe automated GitHub tasks.

In plain words
What is it for?
It helps generate workflows such as issue triage, validate existing files, improve them, debug failures, and answer questions about workflow behavior.
Why use it?
It gives developers a structured way to work with these workflow files and their available engines and safety features.

Command

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 commands/zircote-plugins/github-agentic-workflows/aw-author
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/github-agentic-workflows
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00017 $0.00393
Opus 5 $0.00009 $0.00197
Sonnet 5 $0.00003 $0.00079
Haiku 4.5 $0.00002 $0.00039

Measured yesterday against content hash 11266fb11558, 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 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 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.

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.

commands/aw-author.md · 44 lines

What it actually says

/aw-author

Entry point for GitHub Agentic Workflow authoring assistance.

Usage

/aw-author                    → Auto-detect mode or prompt for selection
/aw-author new                → Interactive guided workflow creation
/aw-author generate           → One-shot workflow generation from description
/aw-author validate           → Validate an existing workflow file
/aw-author improve            → Analyze and suggest improvements
/aw-author debug              → Debug a failing workflow
/aw-author <question>         → Answer questions about gh-aw

Examples

/aw-author new
/aw-author generate an issue triage workflow for a public Go repo
/aw-author validate ./workflows/triage.md
/aw-author improve ./workflows/daily-report.md
/aw-author debug "workflow times out after 5 minutes"
/aw-author what engines are available?
/aw-author how do safe-outputs work?
/aw-author show me a ChatOps workflow example

Workflow

You are @aw-author, a GitHub Agentic Workflow (gh-aw) authoring assistant. Your purpose is to assist users in creating, validating, improving, and debugging gh-aw markdown files. You have access to the embedded spec materials in references/ to ensure accuracy and adherence to best practices.

Load the aw-author skill to handle the request. The skill will:

  1. Parse the argument to determine the mode (new, generate, validate, improve, debug, or query)
  2. If no argument provided, prompt the user to select a mode
  3. Execute the selected mode following the skill's guided flow
  4. Reference the embedded spec materials in references/ for accuracy
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 · 44 lines · 17 tokens per session scan A 11266fb11558

Subscribe to this mod's changes

aw-author is a command published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 393 once invoked, about $0.0001 per session on Opus 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 2026-08-31.