sub-agents CLAUDE.md

sub-agents CLAUDE.md is an instructions file for Claude Code from Toskysun/sub-agents. It costs 1,940 tokens per session, scanned A, original, MIT.

Repository instructions for an AI development team that encourages using specialized agents, browser automation, and documentation research. Browser automation means controlling and inspecting web pages through development tools.

In plain words
What is it for?
Assigning specialized coding work, testing web applications, checking interfaces, capturing screenshots, analyzing performance, and researching repositories or library documentation.
Why use it?
They define when to delegate work and when to use available tools, reducing missed checks during coding, testing, and research.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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 instructions/toskysun/sub-agents/claude-md
Clone the repo
git clone --depth 1 https://github.com/Toskysun/sub-agents

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 sub-agents CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/toskysun/sub-agents/claude-md.svg)](https://agentmods.dev/instructions/toskysun/sub-agents/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/toskysun/sub-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/toskysun/sub-agents/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,940 This file is loaded in full into every session.
When invoked 1,940 The same file — it is already loaded in full.
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 5.1 $0.01940 $0.01940
Opus 5 $0.00970 $0.00970
Sonnet 5 $0.00388 $0.00388
Haiku 4.5 $0.00194 $0.00194

Measured 6d ago against content hash 8a5d9acd372b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

sub-agents 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 6d 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.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intelligent AI Development Team - Proactive Mode

You have access to a complete AI development team. PROACTIVELY invoke specialized agents to deliver high-quality results. When in doubt, use an agent - specialized expertise is always better than generalist handling.

Core Philosophy: Agent-First Approach

  • Default to agents: If a task touches code, architecture, or specialized knowledge, use an agent
  • Parallel execution: Launch multiple agents simultaneously when tasks are independent
  • MCP tools integration: Always consider MCP tools for browser automation, documentation lookup, and external services

MCP Tools - Active Integration

Browser Automation (chrome-devtools)

Proactively use for:

  • Web application testing and debugging
  • UI interaction verification
  • Performance analysis with traces
  • Screenshot capture for documentation
  • Form filling and workflow automation

Key tools: take_snapshot, click, fill, navigate_page, take_screenshot, performance_start_trace

Documentation & Research (deepwiki)

Proactively use for:

  • Understanding GitHub repositories
  • Looking up library documentation
  • Exploring open source project structures

Key tools: read_wiki_contents, ask_question, read_wiki_structure

Web Research (WebSearch, WebFetch)

Proactively use for:

  • Latest technology updates
  • API documentation
  • Best practices lookup
  • Troubleshooting errors

Agent Activation Matrix

Immediate Activation (No Hesitation)

Task Type Agent(s) Trigger Keywords
Vue/Nuxt development vue-developer vue, nuxt, composition api
React/Next development react-developer react, next, hooks, jsx
Backend API backend-developer, fastapi-expert, flask-expert api, endpoint, server, database
Android apps android-developer android, kotlin, gradle
Android hooking android-hooking-expert, xposed-developer hook, frida, xposed, bypass
Go services go-architect golang, go service, grpc
Rust systems rust-architect rust, cargo, memory safety
Spring/Java spring-architect, java-developer spring, java, maven
Lua scripting lua-developer lua, script, game
Infrastructure devops-engineer docker, k8s, ci/cd, deploy
Code review code-reviewer (pr-review-toolkit) review, pr, pull request
Testing test-expert, qa-engineer test, coverage, quality
Architecture cto, technical-solution-architect architecture, design, scalable
Research technical-researcher evaluate, compare, research
UI/UX mobile-ui-designer, google-ui-designer design, ui, ux, material
Security malware-analyst, reverse-engineer security, vulnerability, reverse
Feature planning product-manager requirements, user story, prd

Read the full file on GitHub · 235 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. 6d ago First seen · 235 lines · 1,940 tokens per session scan A 8a5d9acd372b

Subscribe to this mod's changes

sub-agents CLAUDE.md is an instructions file published in the GitHub repository Toskysun/sub-agents (111 stars, last pushed 7mo ago), licensed MIT. It adds 1,940 tokens to every session, about $0.0097 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.