Panel

Put one task in front of four agent CLIs — grok, claude, codex, agy — run each in its own subagent, headless, then report a single consensus grouped by how much the panel agrees.

Each CLI runs as its own latest/default model. Never pass --model to any of them. The point of the panel is four independent models; pinning a model defeats it.

Two task shapes:

• Prompt — the user's text goes to all four, unchanged.
• Review — pin one diff scope and tell all four to review it, read-only, same scope each.

Process

1. Read the task and pick the shape