model-tiering

Select model tiers for subagent roles in a multi-phase build-loop.

1|Updated Apr 6, 2026

Search Tags:#performance-tuning #model-selection #agent-configuration #build-loop #model-tiering

Ready to run

npx skills add https://github.com/tyroneross/build-loop --skill model-tiering-tyroneross

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-tiering
Source: https://github.com/tyroneross/build-loop/tree/main/skills/model-tiering
Command: npx skills add https://github.com/tyroneross/build-loop --skill model-tiering-tyroneross

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Helps to select the right model tier or segment for subagents in the build-loop, defining role descriptors (segment + tier) in frontmatter, and escalating mid-flow.

Core Features & Use Cases

Model Tier Selection: Determines the best model tier for a subagent's role.
Role Descriptors: Provides authoritative guidance on selecting appropriate segment and tier combinations for roles.
Mid-Flow Escalation: Assists in making decisions about model selection and escalating during the build-loop process.

Quick Start

Use the model-tiering skill to choose a model tier for a specific agent role within your build-loop setup.

Frequently Asked Questions about model-tiering

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

FAQPage Schema

How do I select the right model tier for subagents in a build-loop?▼

To select the right model tier for subagents, define role descriptors using segment and tier combinations in the agent frontmatter, then match those roles to a model capability ladder to find the optimal fit for each build-loop phase.

What is model tiering and when do I need it for agent configuration?▼

Model tiering is the process of segmenting models by capability to assign appropriate tiers to subagents. You need it when configuring multi-phase build-loops to ensure each agent role gets the right level of model performance.

Can I escalate a subagent to a higher model tier mid-flow during a build-loop?▼

Yes, you can escalate subagents mid-flow. The model-tiering process provides decision-making guidance for escalating model selection during the build-loop when an agent's current tier lacks the capability to complete its assigned task.

What do I need to set up before implementing model tier selection for agents?▼

You need a taxonomy for model segmentation and capabilities, plus a mechanism for resolving model availability. These prerequisites allow the tiering process to accurately match subagent roles to the correct model segments.

What's the best way to define role descriptors for agent model selection?▼

The best way to define role descriptors is to specify segment and tier combinations directly in the agent frontmatter, using an authoritative capability ladder to ensure the selected tier matches the work role's requirements.

Why does my subagent model selection fail when resolving availability in the build-loop?▼

Model selection fails when the mechanism for resolving model availability cannot map the requested segment and tier to an accessible model, requiring you to verify your model taxonomy and availability resolution setup.