Model Check

Recommends which model — a local model, Codex, or Claude Haiku / Sonnet / Opus — and, for Sonnet and Opus, which effort tier fits the task you're about to do, so you don't default to a high-effort model for simple work. Also decides when a task should be split across an orchestrator and cheaper worker subagents rather than run on one model. Use this whenever you run /model-check, ask "what model should I use", "is this overkill for Sonnet High", "do I need Opus for this", "is this a Haiku task", "should Codex handle this", "should I offload this locally", "should I use high effort", "should I split this into subagents", "would an orchestrator help here", or similar meta-q…