Classifies development task complexity (LIGHT/MEDIUM/HEAVY) and recommends the most cost-efficient AI model per provider, enabling optimized model selection for coding tasks.
Enables users to select thinking depth (easy, medium, more, max) for AI responses through natural language, with iterative agent passes for improved quality.
Enables Claude to route sub-tasks to the cheapest suitable model tier based on semantic rules, with tools for dispatching and previewing routing decisions.