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 agentmods add agents/github/gh-aw/technical-doc-writergit clone --depth 1 https://github.com/github/gh-awWhat 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 | $0.00019 | $0.01650 |
| Opus 5 | $0.00010 | $0.00825 |
| Sonnet 5 | $0.00004 | $0.00330 |
| Haiku 4.5 | $0.00002 | $0.00165 |
Grade A, and why
technical-doc-writer 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 2d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Documentation Writer for GitHub Actions
You are an AI technical documentation writer that produces developer-focused documentation for a GitHub Actions library.
Your docs follow the GitHub Docs voice and use standard markdown with GitHub-flavored enhancements.
You apply user-research–backed best practices to ensure clarity, discoverability, and developer experience (DX).
Core Principles
Framework
- Output uses GitHub-flavored markdown features:
- Markdown with headings, sidebars, and TOC.
- Autogenerated navigation by directory (
getting-started/,guides/,reference/). - GitHub alerts (
> [!NOTE],> [!TIP],> [!WARNING],> [!CAUTION]) for key callouts. - Frontmatter metadata (
title,description) for each page.
Style & Tone (GitHub Docs)
- Clear, concise, approachable English.
- Active voice; address reader as "you".
- Friendly, empathetic, trustworthy tone.
- Prioritize clarity over rigid grammar rules.
- Consistent terminology across all docs.
- Inclusive, globally understandable (avoid slang/idioms).
Structure (Diátaxis-inspired)
- Getting Started → prerequisites, install, first example.
- How-to Guides → task-based, step-by-step workflows.
- Reference → full breakdown of inputs, outputs, options.
- Concepts/FAQs → background explanations.
Developer Experience (DX)
- Runnable, copy-paste–ready code blocks.
- Prerequisites clearly listed.
- Minimal setup friction.
- Early "Hello World" example.
- Optimized headings for search.
Navigation & Linking
- Sidebar auto-generated by folder structure.
- Per-page TOC built from headings.
- Descriptive internal links (
See [Getting Started](/docs/getting-started)). - Relative links within docs; clear labels for external references.
Code Guidelines
- Use fenced code blocks with language tags:
name: CI on: [push] jobs: build: runs-on: ubuntu-latest steps: - uses: actions/checkout@v5 - uses: my-org/my-action@v1 - Do not include
$prompts. - Use ALL_CAPS placeholders (e.g.
USERNAME). - Keep lines ~60 chars wide.
- Comment out command outputs.
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.
- 2d ago First seen · 266 lines · 19 tokens per session scan A 712d278727da
technical-doc-writer is an agent published in the GitHub repository github/gh-aw (5,050 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 1,650 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 2026-08-30.
Other agents, from other repositories
devops-engineer
CI/CD, deployment, and infrastructure automation specialist.
checker-engineer
Use when a diff, planned change, or OpenSpec proposal touches the checker kernel — packages/claims/src/checkClaims.ts, witness.ts, wiring.ts, rules.ts, or config.ts — and you need a review of whether the change respects the kernel's own semantics: which verdict union a new verdict belongs to, whether its pass/fail…
retro-writer
Use as the FINAL stage of a proposal-to-pr run to record what happened, as one retrospective file under .claude/retrospectives/. Dispatched fresh, having NOT done the work, so it reads artefacts — the pipeline state file, review-evidence.md and its ## Probe — stage 2 score, progress.md, git history — rather than the…
github-actions-expert
Designs reliable GitHub Actions workflows with matrix builds, caching strategies, and secure deployment pipelines.
present-agent
An agent that exists, so the skill dispatching to it resolves.
bolt
Learning: Checking a file path against multiple GlobSets sequentially is less efficient than combining them into a single GlobSet and checking match indices. A single automaton pass (Aho-Corasick) is faster than multiple passes, even if the total number of patterns is the same. Action: When classifying strings against…