
Use when the user runs /llm-login or wants to authenticate an LLM provider (GitHub Copilot, Kimi, MiniMax, GLM, Qwen), check auth status, or logout from a provider.
Use when the user wants to chat with a non-Claude model (GPT-4o, Claude via Copilot, Kimi, GLM, MiniMax), get a second opinion from another LLM, compare model responses, or when working on multi-agent tasks that benefit from model diversity. Also use in auto mode when Claude needs to delegate a subtask to the most appropriate available model.