adk-ts: Skill for Claude Code

.claude/skills/adk-ts-readme-writer/SKILL.md

adk-readme-writer is a skill for Claude Code from BrainDAO/adk-ts. It costs 64 tokens per session (2,984 once invoked), scanned A, original, MIT.

A README-writing guide for the ADK-TS monorepo, a single repository containing multiple related packages and apps. It defines the correct structure and wording for root, package, app, and starter-template README files.

In plain words
What is it for?
Use it to create, edit, or review README.md files and to document new ADK-TS packages, apps, or starter templates.
Why use it?
It prevents README files from drifting apart or using the wrong format when packages, apps, or templates are added or changed.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is BrainDAO/adk-ts's own configuration. It tells Claude Code how to work on adk-ts itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything adk-ts configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/BrainDAO/adk-ts/main/.claude/skills/adk-ts-readme-writer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/BrainDAO/adk-ts

Made for: Claude Code.

Wrote 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.

agentmods badge for adk-readme-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/braindao/adk-ts/adk-ts-readme-writer/github.svg)](https://agentmods.dev/skills/braindao/adk-ts/adk-ts-readme-writer)
Your own site
<a href="https://agentmods.dev/skills/braindao/adk-ts/adk-ts-readme-writer"><img src="https://agentmods.dev/badge/skills/braindao/adk-ts/adk-ts-readme-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.

agentmods 80×15 button for adk-readme-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/braindao/adk-ts/adk-ts-readme-writer"><img src="https://agentmods.dev/badge/skills/braindao/adk-ts/adk-ts-readme-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,984 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to high

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 →

  • high Privilege Escalation · line 286
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium MCP Rug Pull · line 273
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 322
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 323
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 320
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 5.1 $0.00064 $0.02984
Opus 5 $0.00032 $0.01492
Sonnet 5 $0.00013 $0.00597
Haiku 4.5 $0.00006 $0.00298

Measured 11d ago against content hash ce7725e090db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

adk-readme-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 11d 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.

.claude/skills/adk-ts-readme-writer/SKILL.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADK-TS README Writer

Overview

This skill creates and updates README files that match the exact branded patterns used across the ADK-TS monorepo. There are four distinct README archetypes — choose the correct one based on where the README lives.

When to Use

  • Creating a new README for a package, app, or starter template
  • Editing an existing README
  • Adding a new package or starter template to the monorepo
  • Reviewing READMEs for consistency

Before Writing

  1. Read the target directory's package.json to extract the package name, description, and version
  2. Identify which archetype applies (see below)
  3. Read the canonical reference README for that archetype
  4. Apply the adk-style-guide skill rules (brand, terminology, URLs)

Archetype 1: Root README

Applies to: README.md (repository root)

Reference file: README.md

Structure:

<div align="center">
  <img src="https://files.catbox.moe/vumztw.png" alt="ADK-TS Logo" width="80" />
  <br/>
  <h1>ADK-TS: The TypeScript-Native AI Agent Framework</h1>
  <b>An open-source framework for building production-ready AI agents in TypeScript. Type-safe, multi-LLM, with built-in tools, sessions, and agent orchestration.</b>
  <br/>
  <i>TypeScript-Native • Multi-Agent Systems • Production-Ready</i>

  <p align="center">
    <a href="https://www.npmjs.com/package/@iqai/adk">
      <img src="https://img.shields.io/npm/v/@iqai/adk" alt="NPM Version" />
    </a>
    <a href="https://www.npmjs.com/package/@iqai/adk">
      <img src="https://img.shields.io/npm/dm/@iqai/adk" alt="NPM Downloads" />
    </a>
    <a href="https://github.com/IQAIcom/adk-ts/blob/main/LICENSE.md">
      <img src="https://img.shields.io/npm/l/@iqai/adk" alt="License" />
    </a>
    <a href="https://github.com/IQAIcom/adk-ts">
      <img src="https://img.shields.io/github/stars/IQAIcom/adk-ts?style=social" alt="GitHub Stars" />
    </a>
  </p>
</div>

---

## 🌟 Overview

## 🚀 Key Features (emoji + link + description bullets)

## ⚡ Quick Start (CLI + manual approaches)

## 📚 Examples

## 🤝 Contributing

## 🌍 Community

## 📜 License

## 🔒 Security

---

**Ready to build your first AI agent?** Visit [https://adk.iqai.com](https://adk.iqai.com) to get started!

Read the full file on GitHub · 394 lines

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. 11d ago First seen · 394 lines · 64 tokens per session scan A ce7725e090db

Subscribe to this mod's changes

adk-readme-writer is a skill published in the GitHub repository BrainDAO/adk-ts (119 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 2,984 once invoked, about $0.0003 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.