AI SummaryControl tmux windows programmatically: create windows, send commands, capture output, and manage processes. Each window gets full screen space for easier output tracking. Window names are visible in the tmux status bar for easy identification. For commands that write to a file (cleaner than capturin
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "automating-tmux-windows" skill in my project. Please run this command in my terminal: # Install skill into your project (2 files) mkdir -p .claude/skills/automating-tmux-windows && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/automating-tmux-windows/SKILL.md "https://raw.githubusercontent.com/majiayu000/claude-skill-registry/main/skills/workflow/automating-tmux-windows/SKILL.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/automating-tmux-windows/metadata.json "https://raw.githubusercontent.com/majiayu000/claude-skill-registry/main/skills/workflow/automating-tmux-windows/metadata.json" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Automates terminal sessions in tmux windows using MCP tools. Use when launching background processes, monitoring builds/servers, sending commands to debuggers (pdb/gdb), interacting with CLI prompts, using interactive commands or commands that require sudo, or orchestrating parallel tasks across multiple terminal sessions.
Instead of calling tmux tools directly, use Task tool:
Task( subagent_type="tmux-runner", description="Run npm build", prompt="Run 'npm run build' in the project directory. Return success/failure and any errors.", model="haiku" # Fast and cheap for simple commands ) ` When to use subagent: • Simple build/test commands • Any command where you just need pass/fail + output • Commands that don't need real-time monitoring When to use direct tmux tools: • Long-running servers you need to monitor over time • Complex interactive debugging sessions • When you need the window to persist across multiple operations
Automating tmux Windows
Control tmux windows programmatically: create windows, send commands, capture output, and manage processes. Each window gets full screen space for easier output tracking. > Note: These tools are provided by the orchestrator MCP server, which also includes AI CLI tools (see ai-orchestration skill).
Recommended: Use Subagent for Context Efficiency
To save context in the main conversation, delegate tmux operations to the tmux-runner subagent: `python
Quick Reference
| Tool | Purpose | | -------------------------------------- | ------------------------------------- | | mcp__orchestrator__tmux_new_window | Create new window with command | | mcp__orchestrator__tmux_send | Send text/keys to window | | mcp__orchestrator__tmux_capture | Get window output | | mcp__orchestrator__tmux_list | List windows (JSON) | | mcp__orchestrator__tmux_kill | Close window | | mcp__orchestrator__tmux_interrupt | Send Ctrl+C | | mcp__orchestrator__tmux_wait_idle | Wait for idle (no output changes) | | mcp__orchestrator__tmux_select | Switch to window (bring to front) | | mcp__orchestrator__tmux_run_and_read | Run command, wait, return file output |
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster