model-selection

Routes AI agent tasks to appropriate model tiers with fallback logic.

3|2|Updated May 12, 2026

Search Tags:#automation #dispatch #ai-orchestration #tiering #model-routing #fleet-management

Ready to run

npx skills add https://github.com/kriscendobot/garden --skill model-selection-kriscendobot

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill manages the complex routing of tasks across a diverse fleet of AI models, ensuring that jobs are assigned to the appropriate tier based on capability, cost, and availability.

Core Features & Use Cases

Tiered Dispatching: Categorizes models into mentat, mentor, minion, and myrmidon tiers to balance performance and cost.
Automatic Routing: Automatically handles fallback logic and provider-specific constraints for fleet jobs.
Use Case: When a high-priority task requires specific reasoning capabilities, this skill ensures the job is routed to the mentor tier, while routine tasks are handled by more cost-effective minion or myrmidon models.

Quick Start

Run the model-selection migration script to normalize existing job tiers and ensure consistent routing across the fleet.

Frequently Asked Questions about model-selection

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

FAQPage Schema

How do I automate dispatching of AI agent tasks across multiple providers?▼

Automated dispatching of AI agent tasks uses centralized routing logic to classify jobs and assign them to a multi-provider model inventory. It enforces tier-based constraints and fallback policies to ensure consistent fleet operations.

What is model tiering and how does it balance performance and cost?▼

Model tiering categorizes a model inventory into mentat, mentor, minion, and myrmidon levels to balance performance and cost. High-priority tasks route to advanced tiers, while routine jobs dispatch to cost-effective models.

How do I set up fallback policies for fleet model routing?▼

Fallback policies for fleet model routing are configured by integrating provider-specific capabilities with centralized routing logic. This approach enforces tier-based constraints to handle job failures or model unavailability.

Can I normalize existing job tiers for consistent model routing?▼

You can normalize existing job tiers by running a model-selection migration script. This script standardizes job classifications to ensure consistent routing across the entire fleet inventory.

How do I route high-priority tasks to specific reasoning capabilities in my fleet?▼

Routing high-priority tasks to specific reasoning capabilities requires the automated dispatching system to match job requirements with the mentor tier. This ensures complex jobs bypass cost-effective minion models for appropriate processing.

What are the limitations of centralized routing logic for multi-provider model fleets?▼

Centralized routing logic limitations depend on the accurate definition of provider-specific capabilities and tier-based constraints. Ineffective tier categorization or missing fallback policies can cause improper job dispatch across the fleet.