Claude Tmux Orchestration — AI skill for Claude Code
Claude Code tmux orchestration — spawn full AI sessions as parallel workers with heartbeat monitoring and file-based coordination.
How to install Claude Tmux Orchestration
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open primeline-ai/claude-tmux-orchestration and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Tmux Orchestration does
Claude Code tmux orchestration — spawn full AI sessions as parallel workers with heartbeat monitoring and file-based coordination.
Alternatives in AI
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Golutra — Multi-agent AI orchestration platform for automation, workflows, and developer tools 3.8k ★
- Omnara — by Ishaan Sehgal - A command center for AI agents that syncs Claude Code sessions across terminal, web, and mo 2.6k ★
README
Claude Code tmux Orchestration - Parallel AI Sessions with Full Context
**Spawn full Claude Code sessions as workers**, coordinated through a bash heartbeat and file-based state. Attach to any of them mid-run and take over by hand.
[](https://primeline.cc/blog/tmux-orchestration) [](https://primeline.cc/guide)

Status: read this before you clone
**Built March 2026. Reviewed 2026-07-31 against current Claude Code. Still runs, but the reason to use it has changed.**
This was built when subagents could not do much. Since then Claude Code absorbed most of it. Per [Anthropic's subagent docs](https://code.claude.com/docs/en/sub-agents), subagent frontmatter now accepts `maxTurns`, `hooks`, `mcpServers`, `skills`, `memory`, `effort`, `background` and `isolation`, and each subagent runs in its own context window.
So the original pitch - "subagents are crippled, use full sessions instead" - is no longer true. **Try subagents first.** They are one file instead of a bash control loop.
| Original claim (March 2026) | Status today |
|---|---|
| Subagents cap at ~25 tool calls | False. maxTurns is a frontmatter field. |
| Subagents get no hook events | False. hooks is configurable per agent; hook events carry agent_id. |
| Subagents cannot reach MCP servers | False. mcpServers is configurable per agent. |
| Subagents share the parent context window | False. Each runs in its own. |
What this still buys you
Three things survive, and only three. If none of them matter, use the native tools.
- A session you can attach to.
tmux attach, watch it work, interrupt it, answer its question by hand, let it continue. No lost context. When a long autonomous run goes sideways at minute 40, taking the wheel is worth the whole control loop. - **Full session lifecycle.
Related Skills
Agents Kit
Conflict-free parallel development on one Git repo by multiple AI coding sessions (Claude Code / Codex). Git-o
Nodeterm
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as dragga
Grove
A Kanban-style TUI for parallel AI coding. Manage Git worktrees as tasks, run multiple agents in isolated tmux
Comandos
Local-first terminal mission control for Claude Code, OpenAI Codex CLI, Gemini CLI and OpenCode. Run AI coding
AI Multi Instance
Local dashboard for running Claude Code, Codex CLI, Cursor Agent, custom commands, and shell sessions in paral
Ntm
Named Tmux Manager: spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Gemini) across tmux
Related Agents
Codex Orchestrator
CLI tool for delegating tasks to GPT Codex agents via tmux sessions. Designed for Claude Code orchestration wi
Booking Checker
Checks ONE activity-watchlist entry against its live provider page and the inbox, and reports what changed. Sp
Subprocess Safety Reviewer
Reviews changes that spawn or control external processes (tmux, git, gh, bash, agent CLIs) and changes touchin