magi

# MAGI Multi-model brainstorming panel. Three teammates explore a question in parallel, each backed by a different model family, then the lead consolidates their proposals for the user. - **Scientist**: reasons directly as Claude Opus (no external dispatch) - **Mother**: delegates to OpenAI Codex via `mcp__codex__codex` MCP tool - **Woman**: delegates to Google Gemini via `gemini` CLI ## Process ### 1. Clarify If the question is underspecified, use `AskUserQuestion` to nail down purpose, constraints, and success criteria. Skip if already clear and actionable. - Ask questions one at a time to refine the idea - Prefer multiple choice questions when possible, but open-ended is fine too - Only one question per message ### 2. Setup Read the personality and reference files, then spawn all teammates in parallel. **Files to read:** - Personalities: [MAGI-1.md](personalities/MAGI-1.md), [MAGI-2.md](personalities/MAGI-2.md), [MAGI-3.md](personalities/MAGI-3.md) - References: [codex.md](references/codex.md), [gemini.md](references/gemini.md) **Create team** with `TeamCreate` using name `magi-{topic}` (e.g., `magi-auth-strategy`). **Spawn all 3 teammates in a single message** (3 parallel `Agent` calls with `team_name` set): | Teammate | `name` | `subagent_type` | Prompt includes | | --------- | ----------- | ----------------- | ----------------------------------------------------------------------- | | Scientist...