adibirzu-plugins

Open the MultiLLM dashboard showing sessions, token usage, costs, and backend status. Use when the user asks about LLM usage, costs, dashboard, or wants to see model statistics.

Route work through the local MultiLLM gateway and decide when to ask other LLMs or helper agents for support. Use the `fusion` model slug for one synthesized answer from a multi-model panel + judge (beats a single model), `auto` to fuse hard prompts and route easy ones, and `/api/council` / `/api/cost/estimate` / `/api/routing/decision` for cost-aware multi-model work. Use when Codex/Claude should leverage GPT, Gemini, OCI GenAI, Antigravity, or local models for second opinions, fusion, architecture review, security review, context handoff, dashboard checks, or multi-device session consolidation.