https://github.com/BayramAnnakov/agent-tower-plugin

I kept copy-pasting the same question between Claude, Codex, and Gemini CLIs - one reviews the other's work, back and forth until I'm satisfied. Decided to automate myself out of the loop.

This is Scott Page's "many model thinking" in action: each model has its own character and blind spots,so triangulating between them often catches things a single model misses.

Three modes: - Deliberate: one agent generates, another reviews, they iterate until consensus - Council: parallel opinions + anonymous peer ranking + synthesis (inspired by Karpathy's llm-council) - Debate: two agents argue pro/con, a third judges

Requires 2+ of: Claude Code, Codex, or Gemini CLI.