model-selection

Select AI models for agent spawns using a 4-layer hierarchy and fallback chains.

3.1k|475|Updated Feb 6, 2026

Search Tags:#agent framework #cost optimization #model selection #ai models #llm orchestration #fallback strategy

Ready to run

npx skills add https://github.com/bradygaster/squad --skill model-selection-bradygaster

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-selection
Source: https://github.com/bradygaster/squad/tree/main/.squad/skills/model-selection
Command: npx skills add https://github.com/bradygaster/squad --skill model-selection-bradygaster

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill ensures the most appropriate AI model is selected for each agent task, optimizing for cost, performance, and specific task requirements.

Core Features & Use Cases

Hierarchical Model Selection: Implements a 4-layer system (User Override, Charter Preference, Task-Aware Auto-Selection, Default) to determine the best model.
Fallback Chains: Defines fallback strategies for model unavailability to ensure task completion.
Use Case: When an agent needs to write code, it automatically selects a high-quality model like claude-sonnet-4.5. For simple logging tasks, it defaults to a cost-effective model like claude-haiku-4.5. If the preferred model is down, it intelligently falls back to an alternative.

Quick Start

Configure the model selection skill to prioritize cost-effective models for non-coding tasks.

Frequently Asked Questions about model-selection

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

FAQPage Schema

How do I optimize LLM costs when orchestrating AI agents?▼

Model selection for AI agents uses a 4-layer hierarchy—User Override, Charter Preference, Task-Aware Auto-Selection, and Default—to match model capability and cost to specific agent task requirements.

What is the best way to implement a fallback strategy for LLM orchestration?▼

A robust fallback strategy defines alternative models in a chain, so if a preferred model like claude-sonnet-4.5 is unavailable, the agent automatically degrades to an alternative to ensure task completion.

How does task complexity adjustment work in AI model selection?▼

Task complexity adjustment maps specific agent roles to appropriate models, automatically selecting high-quality models for coding tasks while defaulting to cost-effective models for simple logging operations.

Can I override automatic model selection for specific agent tasks?▼

Yes, the User Override layer sits at the top of the 4-layer hierarchy, allowing you to manually specify a model and bypass Charter Preference, Task-Aware Auto-Selection, and Default selections for specific agent tasks.

How do I configure agent framework model tiers for cost optimization?▼

Configure model tiers by categorizing available AI models into premium, standard, and fast/cheap tiers, then mapping agent tasks to the appropriate tier based on complexity and cost-effectiveness requirements.

What happens when a selected AI model is unavailable during agent execution?▼

When a selected AI model is unavailable, defined fallback chains engage to intelligently route the agent task to an alternative model, ensuring task completion without manual intervention or failure.