skills.rest
bennybennison
bennybennisonCOMMUNITY
Explore all skills by this author →
GitHub

model-routing

Route model selection to balance quality and cost across task tiers.

Updated Apr 11, 2026
Search Tags:#openai#cost-optimization#model-selection#github-copilot#model-routing#agent-profiles#provider-fallback
One-click install
npx skills add https://github.com/bennybennison/agent-toolkit --skill model-routing-bennybennison
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-routing
Source: https://github.com/bennybennison/agent-toolkit/tree/main/skills/model-routing
Command: npx skills add https://github.com/bennybennison/agent-toolkit --skill model-routing-bennybennison

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the selection of the most appropriate model tier and provider for each task to balance output quality against recurring request cost and quota limits.

Core Features & Use Cases

  • Provider registry and model catalog that map providers and models to tiers and cost multipliers.
  • A routing decision tree that assigns Free, Standard, Premium, or manual Ultra tiers for mechanical tasks, typical development work, deep reasoning, and exceptional cases.
  • Agent model profiles, execution-mode-aware resolution (online, offline, hybrid), provider fallbacks, and per-project overrides for targeted cost or quality changes.

Quick Start

Route a code review task to the appropriate model tier to balance quality and cost.

Frequently Asked Questions about model-routing

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

FAQPage Schema
How do I balance OpenAI model quality and cost for code review and feature implementation?▼

To balance model quality and cost, you can route tasks to appropriate model tiers. A routing decision tree assigns Free, Standard, Premium, or manual Ultra tiers for mechanical tasks, typical development work, and deep reasoning.

What is model routing in agent profiles and how does it handle provider fallbacks?▼

Model routing in agent profiles maps providers and models to tiers and cost multipliers. It applies execution-mode-aware resolution for online, offline, or hybrid setups and implements provider fallbacks for stable deterministic assignments.

Can I apply per-project overrides for model selection and cost optimization?▼

Yes, you can apply per-project overrides for targeted cost or quality changes. This allows you to fulfill provider selection and tiered multipliers while maintaining specific model profile resolution for individual projects.

Does this model routing approach work with GitHub Copilot for architecture planning and security audits?▼

Yes, this model routing approach works with GitHub Copilot for architecture planning and security audits. It applies command overrides and agent assignments to balance output quality against recurring request costs and quota limits.

When should I use manual Ultra tier model selection instead of automatic routing?▼

You should use the manual Ultra tier for exceptional cases instead of automatic routing. This ensures deep reasoning tasks receive the necessary quality when standard Premium tiers cannot fulfill complex execution mode constraints.

Related Skills

Explore More Software Engineering Skills→
itallstartedwithaideaitallstartedwithaidea
31

multi-model-routing

Route tasks to model providers by cost, latency, and circuit-breaker fallback.

Community
Advanced
alexsandrocruzalexsandrocruz

feature-development-workflow

Orchestrate end-to-end feature development workflows across SDLC stages with multi-agent coordination.

Community
Advanced
ChrisFmlycChrisFmlyc

do

Execute SPADES Plans with AI, human, or hybrid task routing.

Community
Advanced
sigridjinethsigridjineth
20

ecomode

Route AI tasks to lower-cost model tiers based on complexity.

Community
Intermediate