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/toskysun/sub-agents/claude-mdgit clone --depth 1 https://github.com/Toskysun/sub-agentsWrote 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/toskysun/sub-agents/claude-md)<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>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 | $0.01940 | $0.01940 |
| Opus 5 | $0.00970 | $0.00970 |
| Sonnet 5 | $0.00388 | $0.00388 |
| Haiku 4.5 | $0.00194 | $0.00194 |
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.
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 |
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.
- 6d ago First seen · 235 lines · 1,940 tokens per session scan A 8a5d9acd372b
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).