By salemaziel
Unified CLI-agent orchestrator. Drives Claude Code, OpenAI Codex, Google Gemini, GitHub Copilot, and Qwen Code CLIs in two modes: persistent tmux worker teams (omc-teams style) and one-shot multi-AI fleet dispatch / debate / review (claude-octopus style). Self-contained — no dependency on omc or octo.
Consult the quintet fleet about: **$ARGUMENTS**
Run a quintet debate on: **$ARGUMENTS**
Check readiness of all quintet providers (claude/codex/gemini/copilot/qwen), tmux, and jq.
Dispatch to the quintet fleet: **$ARGUMENTS**
Run a multi-model quintet review of: **$ARGUMENTS**
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.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
One orchestrator for five coding-agent CLIs. Quintet drives Claude Code, OpenAI Codex, Google Gemini, GitHub Copilot, and Qwen Code through a single entry point, in two complementary modes:
omc-teams model, extended to Copilot and Qwen).consult / debate / review flows (the claude-octopus model).It is self-contained: no runtime dependency on omc or octo. The two upstream projects each covered one half — quintet unifies persistent tmux teams and multi-provider one-shot dispatch across the full set of five CLIs.
| omc-teams | claude-octopus | quintet | |
|---|---|---|---|
| Persistent tmux worker teams | ✅ | ❌ | ✅ |
| One-shot multi-AI fleet / debate / review | ❌ | ✅ | ✅ |
| claude / codex / gemini | ✅ | ✅ | ✅ |
| copilot / qwen | ❌ | ✅ (one-shot) | ✅ (teams + one-shot) |
The novel capability quintet adds: running Copilot and Qwen as persistent coordinating tmux team workers, alongside Claude/Codex/Gemini, under one CLI.
Quintet ships as a plugin/extension for all four major coding-agent CLIs from one repo, distributed via the vdw-claude-plugins marketplace where supported.
Claude Code (marketplace):
/plugin marketplace add salemaziel/omc-octo-quintet
/plugin install quintet@vdw-claude-plugins
OpenAI Codex (marketplace): the repo ships .agents/plugins/marketplace.json. In Codex, run /plugins, switch to the vdw-claude-plugins marketplace tab, and install quintet.
Gemini CLI (extension):
gemini extensions install https://github.com/salemaziel/omc-octo-quintet
GitHub Copilot CLI (plugin): point Copilot at the repo's root plugin.json (it loads skills/ and the .copilot/agents/ conductor). Verify with /skills list and /agent.
quintet binary — no PATH changes neededEvery ecosystem shells out to the same CLI at bin/quintet, bundled inside the installed plugin — quintet never touches your shell PATH. Each host locates it on its own:
${CLAUDE_PLUGIN_ROOT}/bin/quintet, and also exposes the plugin's bin/ on the Bash tool's PATH only while the plugin is enabled (it does not modify your login shell).CLAUDE_PLUGIN_ROOT for plugin compatibility, so the same skills resolve the binary there.~/.gemini/extensions/quintet/bin/quintet.~/.copilot/installed-plugins/.../quintet/bin/quintet.Optional — only if you also want to run quintet by hand in a normal terminal:
ln -s "$PWD/bin/quintet" ~/.local/bin/quintet # standalone CLI use, not required by any plugin
quintet doctor
Requirements: tmux (team mode only), jq (optional), and at least one of the agent CLIs installed and authenticated:
npm install -g @anthropic-ai/claude-code # claude
npm install -g @openai/codex # codex
npm install -g @google/gemini-cli # gemini
npm install -g @github/copilot # copilot (or: brew install copilot-cli)
npm install -g @qwen-code/qwen-code # qwen (free OAuth tier)
# Team mode — persistent tmux workers
quintet team 2:codex,1:gemini,1:qwen "build the export feature" \
--name export --cwd ./repo \
--tasks "implement serializer||add tests||write docs||audit edge cases"
quintet team status export
quintet team capture export w1-codex 80
quintet team send export w2-gemini "focus on the v2 API"
quintet team shutdown export --force
# Fleet mode — one-shot across many models
quintet consult "best way to dedupe a 10M-row stream?" claude,codex,gemini
quintet debate "gRPC or REST for this internal service?"
quintet review "$(git diff HEAD~1)" claude,gemini,copilot
quintet doctor # provider/tmux/jq readiness
quintet providers # per-provider install/auth/ready
/quintet:team · /quintet:fleet · /quintet:consult · /quintet:debate · /quintet:review · /quintet:doctor
quintet-conductor — decomposes a task, picks providers, launches/monitors a team or fleet, and synthesizes results.
npx claudepluginhub salemaziel/omc-octo-quintet --plugin quintetMulti-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.