skills.rest
lbouriez
lbouriezCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

Model Selection

Determines the LLM model for each agent spawn using a layered priority approach.

Updated Mar 27, 2026
Search Tags:#llm#agents#fallback#model-selection#spawn#charter#config.json
One-click install
npx skills add https://github.com/lbouriez/Squad-Templates --skill model-selection-lbouriez
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Model Selection
Source: https://github.com/lbouriez/Squad-Templates/tree/main/Expo-Squad/.copilot/skills/model-selection
Command: npx skills add https://github.com/lbouriez/Squad-Templates --skill model-selection-lbouriez

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Selects the optimal LLM model for each agent spawn, balancing capability and cost while preserving configuration across sessions.

Core Features & Use Cases

  • Persistent model preferences stored in .squad/config.json and applied across sessions.
  • Layered resolution ensures per-agent overrides, global defaults, session directives, and charter preferences guide the spawn choice.
  • Spawn acknowledgments include the resolved model for auditing and debugging.

Quick Start

Configure your first model preference or rely on defaults to initialize model resolution for agent spawns.

Frequently Asked Questions about Model Selection

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

FAQPage Schema
How do I configure LLM model selection for multiple agents?▼

LLM model selection for agents is configured using a layered, priority-based approach. It resolves per-agent overrides, global defaults, and session directives to choose the optimal model for each spawn.

How does model fallback work when spawning agents?▼

Model fallback during agent spawns works by evaluating task context and charter preferences against available options. It selects among 18+ models, applying appropriate fallbacks if the primary model is unavailable.

Can I persist LLM agent preferences across sessions?▼

You can persist LLM agent preferences across sessions by storing them in a .squad/config.json file. This ensures your model selection configuration is automatically applied to future agent spawns.

What is the best way to resolve charter preferences for agent spawns?▼

The best way to resolve charter preferences for agent spawns is using a priority-based resolution system. It evaluates charter preferences alongside per-agent overrides and global defaults to select the right model.

Why does the resolved model need to be embedded at spawn time?▼

The resolved model is embedded at spawn time to provide spawn acknowledgments for auditing and debugging. This ensures full traceability of which LLM model was selected for each specific agent spawn.

Related Skills

Explore More Software Engineering Skills→
elbrunoelbruno
2

Model Selection

Resolve LLM models for agent spawns using layered configuration and task-aware selection.

Community
Intermediate
dotnetdotnet
209

Model Selection

Resolve LLM models per agent spawn via layered first-match-wins hierarchy.

Official
Intermediate
webmaxruwebmaxru
49

Model Selection

Resolve LLM models per agent spawn using a five-layer hierarchy and persist to .squad/config.json.

Community
Advanced
DeDuvaDeDuva
1

model-selection

Assign LLM models to agent spawns using a multi-layer resolution hierarchy.

Community
Advanced