What problem does it solve? Coordinators spawning multiple agents need a consistent, deterministic way to pick the right LLM model for each task without re-deciding every time or ignoring user preferences. ## Core Features & Use Cases - Five-Layer Resolution Hierarchy: Resolves models first-match-wins across persistent config, session directives, charter preferences, task-aware auto-selection, and a hardcoded fallback. - Persistent Preferences: Saves defaultModel and per-agent agentModelOverrides to .squad/config.json so choices survive across sessions. - Tiered Fallback Chains: Retries within the same tier (premium, standard, fast) when a model is unavailable, never falling up in tier. - Use Case: A user says "always use opus for Fenster"; the skill validates the model ID, writes the override to config.json, and every future spawn of that agent acknowledges the resolved model. ## Quick Start Ask the coordinator to set a default model, for example by saying "always use claude-sonnet-4.6 for everything", and it will save the preference and apply it to all future agent spawns.