omc-octo-quintet

Quick-action skill to fan out a question across ready AI provider CLIs (Claude, Codex, Antigravity, Copilot, Qwen, OpenCode) in parallel and synthesize a single recommendation. Use for one-shot advisory queries or when invoking /consult. For deep multi-model debate/review and circuit-breaker behavior, see quintet-fleet-dispatch.

Quick-action skill to run a two-round cross-model debate across ready AI provider CLIs (Claude, Codex, Antigravity, Copilot, Qwen, OpenCode) and synthesize a converged verdict. Use when resolving contested decisions via /debate.

Quick-action diagnostic skill to audit installed CLI binaries and authentication states across Quintet providers (Claude, Codex, Antigravity, Copilot, Qwen, OpenCode). Use when verifying provider pools or diagnosing CLI readiness via /doctor.

Run an Interpretable Context Methodology (ICM) staged folder pipeline with human check gates and edit surfaces. Use for multi-stage debate-build or review-fix workflows.

Verification and intent hygiene for multi-agent team and fleet execution. Use when decomposing tasks across quintet worker teams or verifying work produced by background providers (where workers self-report 'DONE' or outputs may be hallucinated/empty). Focuses on verifying real file artifacts and diffs instead of blindly trusting self-reports. Does NOT mandate running test suites for routine code edits, config tweaks, or version bumps.

Run one-shot multi-AI fleet dispatch with quintet — fan a single prompt to several coding-agent CLIs (claude/codex/agy/copilot/qwen/opencode) 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 (one-shot, not interactive REPLs; each worker runs in a tmux window by default so its output stays visible), then merged. Use when fanning real implementation or review work out to several model CLIs in parallel without driving interactive REPLs, 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, Antigravity / agy, GitHub Copilot, Qwen Code, OpenCode) 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 agy 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.

Orchestrate multi-stage AI workflows using Interpretable Context Methodology (ICM) staged folder pipelines with human check gates and edit surfaces. Use when executing complex compound workflows (e.g. debate -> spec -> worktree implementation -> review -> verify) or two-phase review-and-fix tasks where humans must review intermediate outputs.

Operate persistent quintet worker teams — spawn coding-agent CLIs (claude/codex/agy/copilot/qwen/opencode) 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 agy in parallel to build", "distribute subtasks across models". Not for one-shot multi-model questions — use quintet-fleet-dispatch.

Quick-action skill to run a multi-model code review of a diff or target file across ready AI provider CLIs (Claude, Codex, Antigravity, Copilot, Qwen, OpenCode). Use when reviewing code changes via /review.

Quick-action skill to spawn persistent tmux worker teams across coding-agent CLIs (Claude, Codex, Antigravity, Copilot, Qwen, OpenCode) to implement features and edit files in parallel. Use for team execution via /team. For full lifecycle management, steering, and recovery, see quintet-team-runtime.