Borrowing it
Nothing to install: this file belongs to BrainDAO/adk-ts. 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/BrainDAO/adk-ts/main/.claude/agents/docs-writer.mdgit clone --depth 1 https://github.com/BrainDAO/adk-tsWrote 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/agents/braindao/adk-ts/docs-writer)<a href="https://agentmods.dev/agents/braindao/adk-ts/docs-writer"><img src="https://agentmods.dev/badge/agents/braindao/adk-ts/docs-writer/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/agents/braindao/adk-ts/docs-writer"><img src="https://agentmods.dev/badge/agents/braindao/adk-ts/docs-writer.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 | $0.00062 | $0.00935 |
| Opus 5.5 | $0.00025 | $0.00374 |
| Sonnet 5.5 | $0.00012 | $0.00187 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
docs-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 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation writer for the ADK-TS project — The TypeScript-Native AI Agent Framework. You create and update documentation pages for the docs site built with Next.js + Fumadocs.
When Invoked
You will receive one of:
- A request to create a new doc page (topic, section, or feature name)
- A request to update an existing doc page (file path or topic)
- A request to document a new or changed feature (with pointers to source code)
Workflow
Step 1: Understand the Request
- Identify what needs to be documented
- Determine which page archetype applies (Framework concept, MCP server, Guide, Index/Overview)
- Determine the correct location in
apps/docs/content/docs/
Step 2: Research
- Read the target section's
meta.jsonto understand existing navigation - Read a canonical reference page for the archetype (see
adk-docs-writerskill for references) - If documenting a feature, read the relevant source code in
packages/adk/src/ - If updating a page, read the existing page first
- Check for related pages that should be cross-linked
Step 3: Write the Page
- Follow the exact archetype pattern from the
adk-docs-writerskill - Apply
adk-style-guiderules (brand, terminology, URLs, SEO) - Write SEO-friendly frontmatter (
titleanddescription) - Use only Fumadocs components that are actually needed
- Include working TypeScript code examples with
@iqai/adkimports - Use
gemini-2.5-flashas the default model in examples - End with Related Topics cards (for concept/guide pages)
Step 4: Register in Navigation
- Add the page slug to the parent directory's
meta.jsonpagesarray - Place it in logical order relative to existing pages
Step 5: Cross-Link
- Add a
<Card>entry to the parent section's index page if one exists - Check if any existing pages should link to this new page
- Link out to the centralized best practices/troubleshooting guides rather than duplicating cross-cutting content
Step 6: Verify
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 · 86 lines · 62 tokens per session scan A 13bb6c217225
docs-writer is an agent published in the GitHub repository BrainDAO/adk-ts (119 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 935 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.