multi-llm-reviewlisted

# Multi-LLM Code Review Parallel reviews using gateway MCP tools. Each LLM has different strengths — combine for comprehensive coverage. ## LLM Strengths | LLM | Best For | Sync | Async | |-----|----------|------|-------| | Claude | Architecture, design, quality, docs | `claude_request` | `claude_request_async` | | Codex | Implementation correctness, logic bugs, tests | `codex_request` | `codex_request_async` | | Gemini | Security, edge cases, multimodal context | `gemini_request` | `gemini_request_async` | | Grok (xAI) | Independent fourth perspective for diversity / consensus tie-breaks | `grok_request` | `grok_request_async` | | Mistral Vibe | Independent fifth perspective; uncorrelated with the OpenAI/Anthropic/Google/xAI family; defaults to `--agent auto-approve` | `mistral_request` | `mistral_request_async` | ## Dispatch Defaults Apply these on every dispatch unless the caller has explicitly overridden a rule in the current turn: 1. **Omit `model`** — let the gateway use its configured default per CLI. Nominating a model risks deprecated IDs (`o3`, `o3-pro`, `gpt-4o`, …) and capability mismatches. Call `list_models` only when the caller has asked for a specific variant. 2. **`approvalStrategy:"mcp_managed"`** is the skill dispatch default (the gateway schema default is `"legacy"`). It gates the request before execution; Claude then runs with `--permission-mode bypassPermissions`, Gemini with `--approval-mode yolo`, and Codex still needs `fullAuto:true` for autonom