Multiagents — AI skill for Claude Code
Multi-agent orchestration for Claude Code, Codex CLI & Gemini CLI — spawn AI agent teams that communicate, review code, and coordinate via MCP.
How to install Multiagents
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open zetbrush/multiagents and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Multiagents does
Multi-agent orchestration for Claude Code, Codex CLI & Gemini CLI — spawn AI agent teams that communicate, review code, and coordinate via MCP.
Alternatives in AI
- Cursor Talk To Figma MCP — TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c 7k ★
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Flow Deliver — Multi-AI validation, scoring, and review using Codex and Gemini CLIs (Double Diamond Deliver phase) 2.8k ★
README
multiagents
[](https://www.npmjs.com/package/multiagents) [](https://www.npmjs.com/package/multiagents)
Multi-agent orchestration platform for **Claude Code**, **Codex CLI**, and **Gemini CLI**. Enables AI agents to discover each other, communicate in real-time, coordinate file edits, and work as a team on shared codebases.
Built on [MCP (Model Context Protocol)](https://modelcontextprotocol.io/).
What It Does
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Claude Code │ │ Codex CLI │ │ Gemini CLI │
│ (Engineer) │ │ (Reviewer) │ │ (Designer) │
└──────┬───────┘ └──────┬──────┘ └──────┬──────┘
│ MCP (stdio) │ CodexDriver │
└────────────┬───────┴────────────────────┘
│
┌───────▼────────┐
│ Broker Daemon │ SQLite + HTTP on localhost:7899
│ (singleton) │
└───────┬────────┘
│
┌───────▼────────┐
│ Orchestrator │ MCP server for Claude Desktop
│ (team manager) │ Spawns agents, forwards messages,
└────────────────┘ monitors progress, auto-restarts
- Peer discovery: agents find each other via
list_peers - Real-time messaging: instant for Claude (channel push), <3s for Codex (mid-turn steer), 1-3s for Gemini (piggyback)
- Role assignment:
assign_role,rename_peerat runtime - File coordination: exclusive locks + ownership zones prevent conflicts
- Task lifecycle:
idle → working → done_pending_review → addressing_feedback → approved → released - Review loops:
signal_done → submit_feedback → fix → re-review → approve - Shared knowledge: persistent key-value store for architectural decisions, discovered patterns, and project context — prevents context drift across agents
- **Persistent se
Related Skills
AI Pair Collaboration
/ai-pair, ai pair, dev-team, content-team, team-stopCoordinate heterogeneous AI teams: one creates, two review from different angles. Uses Claude Code's native Ag
Red Queen
Red Queen v2 is a multi-agent orchestration backend powering the Red Queen Council. It features a robust conse
Ntm
Named Tmux Manager: spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Gemini) across tmux
AI Agent Guidebook
Comprehensive guides for AI coding assistants: Claude Code, GitHub Copilot, Gemini CLI. Includes MCP servers,
Agents Can Communicate
Let your AI coding sessions talk to each other. Coordinate parallel work, exchange reviews, and hand off unfin
Herdr Control
Multi-agent orchestration for herdr: spawn/route AI coding agents into tabs and worktrees, sort/colour tabs by
Related Agents
Rust-claude-code-api V0.6.0 Quality Audit Report
Date: 2026-02-11 Auditors: Claude Code (team lead) + Codex (security) + Gemini CLI (API ergonomics) Method: 3-
Protocol Researcher
Verifies facts about vendor agent CLIs, SDKs, protocols and terms (Claude Code, Codex, Gemini CLI, OpenCode, A
Maestro
You are a specialized orchestration agent. Your job is to coordinate multiple agents, manage complex multi-pha