LeoYeAI/agent-master-skills / skills/ai-model-router-v2/skill
skill
VerifiedAI Model Router
Compact, intelligent model routing that just works.
Quick Start
# Install
npx clawhub@latest install ai-model-router
# First run - auto-detects your models
python3 skill/core/router.py "What is Python?"
# List available models
python3 skill/core/router.py --list
How It Works
Your Request → Analyze → Select Model
↓
Simple? → Primary (fast/cheap)
Complex? → Secondary (capable)
Private? → Primary (forced)
Scoring (from model-router-premium)
| Pattern | Points |
|---|---|
| Microservices, architecture | +10 |
| Design, implement, optimize | +5 |
| Explain, analyze, compare | +3 |
| Syntax, example, "what is" | -3 |
Threshold: 5 (simple vs complex)
Features
| Feature | Status |
|---|---|
| Auto-detect local models | ✓ (Ollama, LM Studio) |
| Cloud model registry | ✓ (7 built-in) |
| Privacy detection | ✓ (API keys, passwords) |
| Context tracking | ✓ (conversations) |
| JSON config | ✓ (optional) |
| CLI interface | ✓ |
| Core code size | ~200 lines |
CLI
# Route a task
python3 skill/core/router.py "Design a system"
python3 skill/core/router.py "What is a for loop?"
# Options
--json # JSON output
--force primary # Force primary model
--list # List all models
--status # Show status
Python API
from skill.core.router import RouterCore
router = RouterCore()
result = router.route("Design microservices")
print(result.model_name) # "Claude Opus 4"
print(result.reason) # "complex_task(score=15)"
print(result.confidence) # 0.75
Configuration (Optional)
Create ~/.model-router/models.json:
{
"primary_model": {"id": "ollama:llama3:8b"},
"secondary_model": {"id": "anthropic:claude-opus-4"},
"models": [...]
}
Without config: Auto-detects local + uses cloud registry.
Privacy Protection
Automatically forces primary (local) when sensitive data detected:
- API keys (
sk-...,api_key) - Passwords (
password,passwd) - Tokens (
bearer,secret) - Emails, SSN, credit cards
Files
core/router.py- Core routing engine (~200 lines)modules/detector.py- Auto-detection (optional)modules/context.py- Context tracking (optional)
Inspired By
- model-router-premium: Simple scoring logic, cost-aware routing
- Model Router v1: Full feature set, documentation
This version combines:
- The simplicity of model-router-premium (~200 lines)
- The features of ai-model-router (privacy, auto-detect, context)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |