router
par gigabit-eth
Web & Frontend DevelopmentRésumé
Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity.
Description
Ce que fait ce skill
Routes AI agent tasks to the cheapest model capable of handling them. Classifies work into routine, moderate, and complex tiers, then maps each to free through premium model options with pricing tables. Includes a decision algorithm and OpenClaw configuration for mid-session model switching and sub-agent spawning.
Reduces AI API costs 6-10x by matching task complexity to model capability instead of running everything on a premium model.
Quand l'utiliser
- Switching to a cheap model mid-session for bulk file reformatting
- Spawning a DeepSeek sub-agent to fetch and parse 50 URLs
- Escalating to Opus when a Sonnet-level model gets stuck on a multi-step bug
- Running overnight endpoint health checks on free-tier models at zero cost
- Batching agentic coding sub-tasks through Qwen3 Coder to cut monthly API spend
Exemple de workflow
User asks: refactor these 30 test files to use the new shared helper
- 1
Classify the task as routine file operations, targeting Tier 1
- 2
Select deepseek/deepseek-chat or qwen/qwen3-coder-next as the dispatch model
- 3
Spawn a sub-agent with an explicit model field set to the Tier 1 choice
- 4
Sub-agent executes refactoring and reports results back to the parent session
- 5
Parent session resumes on its original model without cost bleed from routine work
30 test files refactored at roughly $0.03 instead of $0.45 on Claude Sonnet
Prérequis
- OpenRouter API key from openrouter.ai/keys
Installation
clawhub install gigabit-eth/routerExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.