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 commands/vanzan01/claude-code-sub-agent-collective/vangit clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collectiveWhat 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 | $0.00000 | $0.01727 |
| Opus 5 | $0.00000 | $0.00864 |
| Sonnet 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 3d 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.
- 3d 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 (521 stars, last pushed 4mo 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.
Other commands, from other repositories
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
multi-agent-optimize
The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improve system performance through intelligent, coordinated agent-based optimization. Leveraging cutting-edge AI orchestration techniques, this tool provides a comprehensive approach to performance engineering across multiple…
ship-an-mcp-server
Workflow recipe — make your product agent-usable by chaining 4 skills, spec to pricing.
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
loop-forge
Turn a one-line repetitive task into a reusable, self-guarding slash command (loop-forge).