By hummer98
Orchestrate multi-agent development teams with cmux-team to spawn, monitor, and coordinate parallel sub-agents in isolated git worktrees, automatically sync documentation with code changes, and analyze task session histories for retrospection.
Activated when running as a cmux-team sub-agent. Triggers: .team/team.json exists AND current session was spawned by Conductor (detect via: initial prompt contains "[CMUX-TEAM-AGENT]" marker). Provides: output protocol, task creation, inter-agent coordination.
cmux-team のメトリクス解析・cohort 比較・介入評価・複数 task 横断トレンド・ trace DB 探索を DuckDB SQL で行うスキル。Triggers: 「メトリクス解析」 「cohort 比較」「介入評価」「baseline 比較」「複数 task の傾向」「時系列 trend」 「trace DB から〜」「DuckDB で〜」「§11 spec の SQL を実行」等の発言。 per-task 履歴の分析は trace-task skill を使う(per-task 履歴 = trace-task / 複数 task・時系列・cohort = 本 skill)。
Use when reading GitHub issues / PRs (github.com or GitHub Enterprise) from the current project. Triggers: mention of an issue/PR number (e.g. "#272", "issue 272", "PR #42"), user asks to run `gh issue`, `gh pr`, `ghe issue`, `ghe pr`, wants to see review / comment status, or asks "show me open issues / review requests / recent closed PRs". Use `cmux-team issue` / `cmux-team pr` / `cmux-team gh` instead of invoking `gh` directly for READ operations — the local SQLite cache avoids rate limit exhaustion. Writing (create / comment / close / merge / review) still goes through `gh`.
cmux-team のヘルプ・リファレンス(読み取り専用)。使い方の説明、概念の解説、 CLI コマンドリファレンス、トラブルシューティングを提供する。 Triggers: 「cmux-team の使い方」「〜とは」「ヘルプ」「help」「how to」等の 質問・解説リクエスト。操作の実行自体は cmux-team スキルが担当。
Use when orchestrating multi-agent development via cmux. Triggers: .team/ directory exists, user says "team", "spawn agents", "parallel", "sub-agent", or any /team-* command is invoked. Provides: agent spawning, monitoring, result collection, synchronization protocols.
Modifies files
Hook triggers on file write and edit operations
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.

Multi-agent development orchestration with Claude Code + cmux.
https://github.com/user-attachments/assets/1d402a69-f48c-4a43-b52d-9c80f0f90ea1
Claude Code's built-in sub-agents are useful, but you can't see what they're doing. You only get the final result — the process is a black box.
This matters more than it might seem. When AI agents work invisibly, two problems compound:
cmux-team is an AI observatory, not another automation black box. The terminal panes aren't decoration — they're the product. A 10-second glance at a Conductor pane is often enough to catch a problem that would otherwise only surface at the end.
To peek into another project's runtime state without leaving your shell: cmux-team status --project-root /path/to/other (read-only by default; cross-project writes require --project-root-confirm or CMUX_TEAM_PROJECT_ROOT_CONFIRM=1).
The design principle: reduce cognitive load by making the process visible, not by hiding it.
What you do: Give Claude instructions in natural language. What Claude does: Splits panes via cmux, launches sub-agents, monitors them, and integrates results — all in plain sight.
brew install --cask font-hack-nerd-font
Works without Nerd Font (falls back to Unicode symbols). Set CMUX_NERD_FONT=0 to use fallback icons explicitly.npm install -g @hummer98/cmux-team
The daemon detects new versions via update-notifier and surfaces them in the TUI banner. Install is always manual — run npm i -g @hummer98/cmux-team@<latest> yourself to avoid surprises across mixed Node environments (Volta / nvm / Homebrew).
Two modes (default: off):
| mode | behavior |
|---|---|
off | do nothing (no registry access) |
notify | detect every 12h and show a TUI banner; no install |
Configuration (precedence: env > config > default):
CMUX_TEAM_AUTO_UPDATE=off|notify (also accepts 0|false as off).team/config.json: { "autoUpdate": "off" | "notify" }Related:
NO_UPDATE_NOTIFIER=1 disables detection (standard update-notifier env var)auto_update_config mode=<mode> source=<env|config|default>Breaking change (v4.5.0, T294):
task mode (auto-creation of update tasks) is removed. CMUX_TEAM_AUTO_UPDATE=task|1|true and .team/config.json: autoUpdate: "task" | true | false now exit with status 1.cmux-team self-update subcommand is removed.autoUpdate to notify (or off), then run npm install -g @hummer98/cmux-team@latest when the banner appears..team/config.json)Created per-project by cmux-team start. All keys are optional — the file can be edited by hand and is re-read on next start. General precedence: CLI flag > env var > .team/config.json > built-in default.
Skill for operating cmux terminal multiplexer. Pane splitting, sub-agent spawning/monitoring/result collection, command sending, screen reading, and notifications.
npx claudepluginhub hummer98/cmux-team --plugin cmux-teamMulti-agent orchestration for Claude Code. 12 specialized agents working in parallel — planning, building, reviewing, debugging. Plus a Hub for always-alive multi-project sessions controllable from Telegram or Slack.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Repowire mesh usage skills for AI coding agents: cross-agent review and planning, delegate, usage patterns, and install/update. Backend-agnostic and parameterised on the agent you choose.
MCP server for spawning and orchestrating multiple Claude Code sessions via iTerm2
Marketplace for the Agency CLI - an AI agent orchestrator
AI team role and worker manager for multi-agent development workflows.