model-routing

Route subagents to the cheapest sufficient model across task types.

Updated Aug 27, 2026

Search Tags:#ai #subagents #cost-optimization #fallback #task-dispatch #model-routing #routing-table

Ready to run

npx skills add https://github.com/ItsMattG/property-tracker --skill model-routing

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-routing
Source: https://github.com/ItsMattG/property-tracker/tree/main/.claude/skills/model-routing
Command: npx skills add https://github.com/ItsMattG/property-tracker --skill model-routing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Route subagents to the cheapest sufficient model to optimize cost and resource use.

Core Features & Use Cases

Route decisions map each task type to a model that is cost-efficient yet capable.
Fallback escalation: haiku -> sonnet -> opus to handle failures and maintain throughput.
Use cases include exploratory searches, simple edits, multi-file implementation, and architecture reviews in autonomous AI workflows.

Quick Start

Balance cost and capability by mapping each task type to the cheapest model that can complete it.

Frequently Asked Questions about model-routing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I route AI subagents to the cheapest sufficient model?▼

Model routing assigns each task type to the cheapest capable model using a configurable routing table, optimizing cost and performance across autonomous workflows.

What is the fallback escalation path when a model fails during task dispatch?▼

The fallback escalation path for task dispatch is haiku to sonnet to opus. This tiered routing strategy handles failures and maintains throughput by upgrading to more capable models as needed.

How does cost-aware routing work for multi-file implementation and code reviews?▼

Cost-aware routing works by mapping task types like multi-file implementation and code reviews to specific models in a routing table, ensuring exploratory searches use cheaper models while architecture tasks use capable ones.

Can I use a custom routing table for autonomous AI workflow task dispatch?▼

Yes, you can use a custom routing table for autonomous AI workflow task dispatch. The routing table is configurable, allowing you to balance cost and capability by mapping each task type to preferred models.

When should I not use the cheapest model for AI task routing?▼

You should not use the cheapest model for AI task routing when handling complex architecture reviews or multi-file implementations that exceed its capability. The tiered fallback escalation to sonnet or opus handles these failures.