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/vanzan01/claude-code-sub-agent-collective/claude-mdgit clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collectiveWrote 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/vanzan01/claude-code-sub-agent-collective/claude-md)<a href="https://agentmods.dev/instructions/vanzan01/claude-code-sub-agent-collective/claude-md"><img src="https://agentmods.dev/badge/instructions/vanzan01/claude-code-sub-agent-collective/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 | $0.02366 | $0.02366 |
| Opus 5 | $0.01183 | $0.01183 |
| Sonnet 5 | $0.00473 | $0.00473 |
| Haiku 4.5 | $0.00237 | $0.00237 |
Grade A, and why
claude-code-sub-agent-collective 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 — 270 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
This is the Claude Code Sub-Agent Collective - an NPX-distributed framework that installs specialized AI agents, hooks, and behavioral systems for TDD-focused development workflows. The system enforces test-driven development through automated handoff validation and provides intelligent task routing through a hub-and-spoke architecture.
CRITICAL REPOSITORY INFORMATION
Git Remote URL: https://github.com/vanzan01/claude-code-sub-agent-collective.git NEVER CHANGE THIS URL - Always use this exact repository URL for all git operations.
Architecture
Core System
- Hub-and-spoke architecture with
@routing-agentas central coordinator - Behavioral Operating System defined in
CLAUDE.mdwith prime directives - Test-Driven Handoffs with contract validation between agents
- Just-in-time context loading to minimize memory usage
Key Components
- NPX Package:
claude-code-collective- Installable vianpx claude-code-collective init - Agent System: 30+ specialized agents in
templates/agents/ - Hook System: TDD enforcement hooks in
templates/hooks/ - Command System: Natural language + structured commands in
lib/command-*.js - Metrics Framework: Research hypotheses tracking in
lib/metrics/ - Template System: Installation templates in
templates/
Essential Commands
Development
# Run tests (primary test suite)
npm test # Vitest tests
npm run test:jest # Jest tests (comprehensive)
npm run test:coverage # Coverage reports
# Run specific test suites
npm run test:contracts # Contract validation tests
npm run test:handoffs # Agent handoff tests
npm run test:agents # Agent system tests
# Package management
npm run install-collective # Install to current directory
npm run validate # Validate installation
npm run metrics:report # View metrics data
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 · 270 lines · 2,366 tokens per session scan A 483eda87e745
claude-code-sub-agent-collective CLAUDE.md is an instructions file published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 2,366 tokens to every session, about $0.0118 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
orchestkit CLAUDE.md
Claude Code instructions for yonatangross/orchestkit, covering claude.md, language, tone, visuals and project overview.
orchestkit AGENTS.md
AGENTS.md instructions for yonatangross/orchestkit, covering agents.md, the one rule that prevents most broken prs, build and verify, adding a component and working conventions.
don-cheli-sdd GEMINI.md
Gemini CLI instructions for doncheli/don-cheli-sdd, covering don cheli — instructions for google antigravity, identity, context files, iron laws (non-negotiable) and deviation rules.
don-cheli-sdd CLAUDE.md
Claude Code instructions for doncheli/don-cheli-sdd, covering don cheli — instrucciones para claude code, identidad, archivos de contexto, leyes de hierro (no negociable) and reglas de desviación.
don-cheli-sdd AGENTS.md
AGENTS.md instructions for doncheli/don-cheli-sdd, covering don cheli — instructions for codex and other agents, cross-tool compatibility, identity, context and rules.
specwright AGENTS.md
AGENTS.md instructions for Obsidian-Owl/specwright, covering specwright, workflow, anchor documents, architecture and operator notes.