analyze
01Command
Analyze recent runs (latency, tokens, verdict agreement) and suggest model/reasoning/fanout tuning.
Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures which models earn their seat.
Command
Analyze recent runs (latency, tokens, verdict agreement) and suggest model/reasoning/fanout tuning.
Command
Ask GPT, Gemini, Grok, and OpenRouter in parallel for independent second opinions.
Command
Ask Gemini for a single-shot second opinion.
Command
Ask GPT (Codex) for a single-shot second opinion.
Command
Ask Grok (xAI) for a single-shot second opinion.
Command
Ask a configured OpenRouter model for a single-shot second opinion.
Command
Fan out, then run one arbiter pass that synthesizes a single verdict.
Command
Check deliberation's health - config, provider CLIs, sessions/debug, and path drift - and suggest fixes. Read-only; never changes anything.
Command
List, prune, or gc Grok (xAI) uploaded files. Cleanup for bridge-owned uploads only.
Command
Show how to use deliberation here - what each command does, when to reach for it, and real prompts you can paste right now. Read-only.
Command
Configure deliberation with Codex (GPT), Gemini, Grok, and OpenRouter MCP servers.
Command
Uninstall deliberation (remove MCP config and rules).