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.
git 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/commands/vanzan01/claude-code-sub-agent-collective/van)<a href="https://agentmods.dev/commands/vanzan01/claude-code-sub-agent-collective/van"><img src="https://agentmods.dev/badge/commands/vanzan01/claude-code-sub-agent-collective/van/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.
<a href="https://agentmods.dev/commands/vanzan01/claude-code-sub-agent-collective/van"><img src="https://agentmods.dev/badge/commands/vanzan01/claude-code-sub-agent-collective/van.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01727 |
| Opus 5.5 | $0.00000 | $0.00691 |
| Sonnet 5.5 | $0.00000 | $0.00345 |
| Haiku 4.5 | $0.00000 | $0.00173 |
Grade A, and why
van 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 2mo 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/van - Collective Routing Engine
allowed-tools: Task(), Read(), Write(), Edit(), MultiEdit(), Glob(), Grep(), Bash(), LS(), TodoWrite(), WebSearch(), WebFetch(), mcp__task-master__, mcp__context7__ description: 🚐 Fast routing engine for intelligent agent selection and request delegation
🎯 Purpose - Smart Routing
Fast Agent Selection - analyze user requests and route to the optimal specialized agent using proven patterns and decision matrices.
🚐 Routing Flow
Request → 🧠 Quick Analysis → 🎯 Agent Selection → ⚡ Task Delegation
🚀 DUAL-MODE ROUTING PROTOCOL
🎯 USER IMPLEMENTATION MODE (Direct Agent Routing - DEFAULT)
Triggers: Feature implementation, code creation, bug fixes, testing, research
Pattern: Direct routing to specialized implementation agents
No TaskMaster: Bypass research coordination for practical development
🔬 RESEARCH COORDINATION MODE (TaskMaster Integration - RARE)
Triggers: System management, research project coordination, collective enhancement
Pattern: Complex coordination through TaskMaster workflows
Full Orchestration: Use enhanced TaskMaster agents (task-orchestrator → task-executor → task-checker)
🧠 IMMEDIATE AGENT ROUTING
Bypass analysis for obvious requests:
| User Says | Instant Agent | Why Skip Analysis |
|---|---|---|
| "build/create/implement X" | @component-implementation-agent OR @feature-implementation-agent | Direct implementation needed |
| "build app from PRD" | @prd-parser-agent | Parse PRD → research → generate tasks |
| "create app from PRD" | @prd-parser-agent | Parse PRD → research → generate tasks |
| "create application using PRD" | @prd-parser-agent | Parse PRD → research → generate tasks |
| "implement from PRD" | @prd-parser-agent | Parse PRD → research → generate tasks |
| "execute tasks" | @task-orchestrator | Coordinate existing TaskMaster tasks |
| "fix/debug/resolve X" | @feature-implementation-agent | Direct problem-solving |
| "test/validate X" | @testing-implementation-agent | Direct testing workflow |
| "optimize/polish X" | @polish-implementation-agent | Direct improvement |
| "research/analyze/compare X" | @research-agent | Direct research needed |
| "setup/configure build" | @infrastructure-implementation-agent | Direct infrastructure work |
| "review/check quality" | @quality-agent | Direct quality validation |
| "deploy/setup devops" | @devops-agent | Direct deployment work |
| "enhance collective" | @task-orchestrator | System-level coordination |
| "coordinate complex project" | @task-orchestrator | Multi-agent orchestration |
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.
- 2mo ago First seen · 150 lines · 0 tokens per session scan A b2c4f05995d9
van is a command published in the GitHub repository vanzan01/claude-code-sub-agent-collective (525 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,727 tokens. 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.
van compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vanvanzan01/claude-code-sub-agent-collective | Command | 525 | 6mo ago | MIT | A | 0 | Claude Code |
| review-pryonatangross/orchestkit | Command | 299 | yesterday | MIT | A | 40 | Claude Code, Cursor |
| fix-issueyonatangross/orchestkit | Command | 299 | yesterday | MIT | A | 45 | Claude Code, Cursor |
| implementyonatangross/orchestkit | Command | 299 | yesterday | MIT | A | 50 | Claude Code, Cursor |
| verifyyonatangross/orchestkit | Command | 299 | yesterday | MIT | A | 55 | Claude Code, Cursor |
| create-pryonatangross/orchestkit | Command | 299 | yesterday | MIT | A | 46 | Claude Code, Cursor |
| design-to-codeyonatangross/orchestkit | Command | 299 | yesterday | MIT | A | 54 | Claude Code, Cursor |