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 instructions/braindao/adk-ts/claude-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/instructions/braindao/adk-ts/claude-md)<a href="https://agentmods.dev/instructions/braindao/adk-ts/claude-md"><img src="https://agentmods.dev/badge/instructions/braindao/adk-ts/claude-md.svg" alt="Measured on agentmods" 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 | $0.01127 | $0.01127 |
| Opus 5 | $0.00563 | $0.00563 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
adk-ts CLAUDE.md 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 5d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
ADK-TS is the TypeScript-native AI agent framework — a comprehensive toolkit for building sophisticated AI agents with multi-LLM support, advanced tools, and flexible conversation flows. This is a monorepo containing the core framework package, documentation site, examples, and CLI tools.
Development Commands
Core Commands
pnpm install- Install all dependencies across the monorepopnpm build- Build all packages using Turbo (with 50 concurrency)pnpm dev- Start development mode for all appspnpm test- Run tests (usepnpm test --filter=adkfor core package only)pnpm format- Format code using Biomepnpm lint- Run linting using lint-staged
Package-Specific Commands
pnpm build:docs- Build documentation site onlypnpm start:docs- Start docs site in production mode- Core package tests:
cd packages/adk && pnpm testorpnpm test:watchfor watch mode - Single test:
cd packages/adk && pnpm test -- <test-pattern>
Cleanup Commands
pnpm clean- Clean all build outputs via Turbopnpm clean-modules- Remove all node_modules directoriespnpm clean-dist- Remove all dist directories
Architecture
Monorepo Structure
packages/adk/- Core ADK-TS framework package (@iqai/adk) // ...existing code...packages/tsconfig/- Shared TypeScript configurationsapps/docs/- Documentation website (Next.js + Fumadocs)apps/examples/- Comprehensive example implementationspackages/adk-cli/- Official CLI for creating and managing ADK-TS projects.
Core Framework Components
The main framework in packages/adk/src/ is organized into:
Agents (src/agents/)
AgentBuilder- Fluent API for creating agents with different typesLlmAgent- Single LLM-based agentLoopAgent- Agent that can iterate and planParallelAgent- Execute multiple agents concurrentlySequentialAgent- Execute agents in sequenceLangGraphAgent- Graph-based workflow agent
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.
- 5d ago First seen · 146 lines · 1,127 tokens per session scan A 3b604648e086
adk-ts CLAUDE.md is an instructions file published in the GitHub repository BrainDAO/adk-ts (119 stars, last pushed 2mo ago), licensed MIT. It adds 1,127 tokens to every session, about $0.0056 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 instructions, from other repositories
openai-agents-python AGENTS.md
AGENTS.md instructions for openai/openai-agents-python, covering contributor guide, policies & mandatory rules, mandatory skill usage, work status reporting and git worktree and branch safety.
blade-code AGENTS.md
AGENTS.md instructions for echoVic/blade-code, covering agents.md, project overview, quick commands, development and running.
Kokoro-Engine CLAUDE.md
Claude Code instructions for chyinan/Kokoro-Engine, covering claude.md, git 规范, 项目概述, 常用命令 and 安装依赖.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
zypher-agent CLAUDE.md
Instructions for corespeed-io/zypher-agent, covering claude.md, development commands, code quality, architecture overview and monorepo structure.
pcl copilot-instructions.md
Copilot instructions for personamanagmentlayer/pcl, covering project overview, pcl bootstrap system, core architecture principles, 1. compiler pipeline and 2. type system.