skills.rest
humanerd-drew
humanerd-drewOFFICIAL
Explore all skills by this author →
GitHub

model-routing

Automate model selection for AI agents based on task complexity and billing.

2|7|Updated Jun 19, 2026
Search Tags:#AI agent#cost optimization#model routing#model selection#subscription billing
One-click install
npx skills add https://github.com/humanerd-drew/opencode-drewgent --skill model-routing-humanerd-drew
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-routing
Source: https://github.com/humanerd-drew/opencode-drewgent/tree/main/skills/software-development/model-routing
Command: npx skills add https://github.com/humanerd-drew/opencode-drewgent --skill model-routing-humanerd-drew

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires opencode-go, minimax, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill ensures that AI agents use the most cost-effective and capable models for their tasks, balancing performance and efficiency in multi-tiered workflows.

Core Features & Use Cases

  • Cost-Aware Routing: Dynamically assigns models based on capability tier and subscription billing.
  • 3-Tier Model Pyramid: Supports Flash, Pro, and Max models for varying task complexities.
  • Fallback Mechanism: Escalates to a higher-tier model if the current model cannot handle the task.
  • User Preference Integration: Informs all proposals with cost analysis, optimizing for both quality and cost.
  • Provider Auto-Resolution: Selects the most suitable provider for each task.

Quick Start

To start routing tasks to the appropriate model, run: skill("model-routing route").

Frequently Asked Questions about model-routing

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

FAQPage Schema
How do I optimize AI agent model selection for cost and performance?▼

AI agent model selection is optimized by automating routing based on task complexity and subscription billing, ensuring cost-effective and capable models are dynamically assigned across a 3-tier model pyramid.

Can I use OpenCode Go and MiniMax APIs for automated model routing?▼

Yes, automated model routing integrates directly with OpenCode Go and MiniMax APIs, handling provider auto-resolution and fallback logic to select the most suitable provider for each assigned task.

How does fallback logic work when an AI agent cannot handle a task?▼

Fallback logic escalates the task to a higher-tier model when the currently assigned model cannot handle the complexity, ensuring performance is maintained without manual intervention.

What is the best way to route tasks across Flash, Pro, and Max model tiers?▼

Routing tasks across Flash, Pro, and Max tiers is best handled by cost-aware routing, which dynamically assigns models based on capability tier and subscription billing to balance efficiency and quality.

When do I need cost-aware routing for multi-tiered AI workflows?▼

Cost-aware routing is needed when balancing performance and efficiency in multi-tiered workflows, ensuring all proposals are informed by cost analysis to optimize for both quality and expense.

Does model routing support subscription billing for provider auto-resolution?▼

Yes, model routing supports subscription billing by dynamically assigning models based on capability tier and billing status, ensuring provider auto-resolution selects the most suitable provider for cost-effectiveness.

Related Skills

Explore More Software Engineering Skills→
DavidLam-ossDavidLam-oss
283

openprd-requirement-intake

Route product requirements into L0, L1, or L2 development workflows.

Community
Advanced
nextplus896nextplus896

laravel-routing

Configure Laravel routes with model binding and route-level authorization.

Community
Advanced
Habitat-ThinkingHabitat-Thinking
44

cost-tracking

Capture AI provider spend and token usage into structured Markdown cost snapshots.

Official
Intermediate
kriscendobotkriscendobot
3

model-selection

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

Community
Advanced