omc-octo-quintet

Engineering discipline for multi-agent work — lock intent before building, write zero-context plans, and prove claims with fresh evidence before declaring done. Trigger when starting a multi-step task, writing an implementation plan, or about to claim work is complete/fixed/passing (especially after a quintet fleet/team run, where provider output may be hallucinated). Not for trivial single-action edits.

Run one-shot multi-AI fleet dispatch with quintet — fan a single prompt to several coding-agent CLIs (claude/codex/gemini/copilot/qwen) in parallel, run a two-round cross-model debate, or get a multi-model code review, with circuit-breaker and fallback reliability. Use proactively when fanning a prompt out to several models, when running an AI debate, when seeking consensus, or for reviewing a diff across models. Trigger on "quintet fleet", "AI debate", "run a debate between models", "consult the models", "get consensus from the models", "multi-model review", "what do all the models think". Not for parallel file-editing work — use quintet-team-runtime.

Orchestrate multiple coding-agent CLIs (codex/gemini/copilot/claude) headlessly — each in its own git worktree, driven non-interactively, then merged. Use when fanning real implementation or review work out to several model CLIs in parallel without a tmux REPL, when you need worktree isolation so agents don't collide, or when distributing token cost onto external providers. Trigger on "run codex/gemini/copilot in parallel", "headless multi-agent", "git worktree per agent", "non-interactive CLI agents", "offload work to other model CLIs", "parallel build with isolated worktrees". For interactive tmux worker teams use quintet-team-runtime instead; for one-shot opinions use quintet-fleet-dispatch.

Orchestrate multiple coding-agent CLIs (Claude Code, OpenAI Codex, Google Gemini, GitHub Copilot, Qwen Code) as one fleet through the quintet entry point. Use proactively when running several of these AI CLIs at once, when spinning up a multi-agent CLI worker team in tmux, for fanning a single prompt out to many models, or when debating or reviewing across models. Trigger on "quintet", "run codex and gemini and copilot", "orchestrate CLI agents", "ask all the models", "AI debate", "multi-model review". Not for single-model edits or generic multi-agent frameworks unrelated to the quintet CLIs.

Operate persistent quintet worker teams — spawn coding-agent CLIs (claude/codex/gemini/copilot/qwen) as long-lived tmux workers, distribute scoped subtasks, monitor, and shut down. Use proactively when running a multi-agent CLI team in tmux, when distributing work across AI workers, for building or refactoring in parallel, or when recovering a stuck or orphaned quintet team. Trigger on "quintet team", "tmux worker team", "parallel AI workers", "spawn agent workers", "run codex and gemini in parallel to build", "distribute subtasks across models". Not for one-shot multi-model questions — use quintet-fleet-dispatch.