model-hierarchy

Route tasks to the cheapest capable model by complexity tier.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/EveryInc/everyskill --skill model-hierarchy-everyinc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-hierarchy
Source: https://github.com/EveryInc/everyskill/tree/main/skills/model-hierarchy
Command: npx skills add https://github.com/EveryInc/everyskill --skill model-hierarchy-everyinc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cost-efficiently routing AI work by selecting the cheapest model that can complete a task, reducing unnecessary expense and preserving premium models for harder problems.

Core Features & Use Cases

  • Tiered model selection based on task complexity (routine, moderate, and complex) to optimize cost and throughput.
  • Sub-agent spawning on cheaper models to handle large volumes without sacrificing performance.
  • Decision workflow for classification, escalation, and downgrades to maintain quality while controlling spend.

Quick Start

Provide a task description and let the system route it to the cheapest capable model.

Frequently Asked Questions about model-hierarchy

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

FAQPage Schema
How do I route AI tasks to the cheapest capable model?▼

Tiered model selection is a workflow that classifies tasks by complexity into routine, moderate, and complex tiers, selecting the cheapest capable model for each to optimize cost and throughput.

How do I optimize AI operational costs when processing large task volumes?▼

You optimize AI operational costs by spawning sub-agents on cheaper models to handle large task volumes, preserving premium models for harder problems without sacrificing performance.

Does the model routing workflow support task escalation and downgrades?▼

The model routing workflow supports task escalation and downgrades by applying a decision workflow that reclassifies task complexity dynamically to maintain quality while controlling spend.

When should I use sub-agent spawning for AI task classification?▼

Use sub-agent spawning for AI task classification when processing large volumes of routine tasks, allowing the system to execute work on cheaper models to reduce unnecessary expense without sacrificing performance.

What is the best way to preserve premium AI models for complex problems?▼

The best way to preserve premium AI models is to implement a tiered model selection workflow that classifies tasks by complexity, routing routine and moderate work to cheaper capable models.