A structured, multi-model "council" that either REVIEWS material against criteria or DOES the open-ended work asked for, turning either into decisions. Models work independently, then anonymously rank and adjudicate each other's output; a non-Claude "chair" synthesizes the verdict or answer — Claude orchestrates…
Spawn a conversation with another LLM (Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Qwen, Grok, Mistral, or Claude as a target) and fold the results back into your context. TRIGGER when: the user asks to talk to, chat with, call, use, or spawn another LLM or model; names any non-current model; wants parallel exploration…