tmux
Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.
Best use case
tmux is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.
Teams using tmux should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/tmux/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How tmux Compares
| Feature / Agent | tmux | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# tmux Skill
Use tmux as a programmable terminal multiplexer for interactive work. Works on Linux and macOS with stock tmux; avoid custom config by using a private socket.
## Quickstart (isolated socket)
```bash
SOCKET_DIR=${TMPDIR:-/tmp}/claude-tmux-sockets # well-known dir for all agent sockets
mkdir -p "$SOCKET_DIR"
SOCKET="$SOCKET_DIR/claude.sock" # keep agent sessions separate from your personal tmux
SESSION=claude-python # slug-like names; avoid spaces
tmux -S "$SOCKET" new -d -s "$SESSION" -n shell
tmux -S "$SOCKET" send-keys -t "$SESSION":0.0 -- 'python3 -q' Enter
tmux -S "$SOCKET" capture-pane -p -J -t "$SESSION":0.0 -S -200 # watch output
tmux -S "$SOCKET" kill-session -t "$SESSION" # clean up
```
After starting a session ALWAYS tell the user how to monitor the session by giving them a command to copy paste:
```
To monitor this session yourself:
tmux -S "$SOCKET" attach -t claude-lldb
Or to capture the output once:
tmux -S "$SOCKET" capture-pane -p -J -t claude-lldb:0.0 -S -200
```
This must ALWAYS be printed right after a session was started and once again at the end of the tool loop. But the earlier you send it, the happier the user will be.
## Socket convention
- Agents MUST place tmux sockets under `CLAUDE_TMUX_SOCKET_DIR` (defaults to `${TMPDIR:-/tmp}/claude-tmux-sockets`) and use `tmux -S "$SOCKET"` so we can enumerate/clean them. Create the dir first: `mkdir -p "$CLAUDE_TMUX_SOCKET_DIR"`.
- Default socket path to use unless you must isolate further: `SOCKET="$CLAUDE_TMUX_SOCKET_DIR/claude.sock"`.
## Targeting panes and naming
- Target format: `{session}:{window}.{pane}`, defaults to `:0.0` if omitted. Keep names short (e.g., `claude-py`, `claude-gdb`).
- Use `-S "$SOCKET"` consistently to stay on the private socket path. If you need user config, drop `-f /dev/null`; otherwise `-f /dev/null` gives a clean config.
- Inspect: `tmux -S "$SOCKET" list-sessions`, `tmux -S "$SOCKET" list-panes -a`.
## Finding sessions
- List sessions on your active socket with metadata: `./scripts/find-sessions.sh -S "$SOCKET"`; add `-q partial-name` to filter.
- Scan all sockets under the shared directory: `./scripts/find-sessions.sh --all` (uses `CLAUDE_TMUX_SOCKET_DIR` or `${TMPDIR:-/tmp}/claude-tmux-sockets`).
## Sending input safely
- Prefer literal sends to avoid shell splitting: `tmux -L "$SOCKET" send-keys -t target -l -- "$cmd"`
- When composing inline commands, use single quotes or ANSI C quoting to avoid expansion: `tmux ... send-keys -t target -- $'python3 -m http.server 8000'`.
- To send control keys: `tmux ... send-keys -t target C-c`, `C-d`, `C-z`, `Escape`, etc.
## Watching output
- Capture recent history (joined lines to avoid wrapping artifacts): `tmux -L "$SOCKET" capture-pane -p -J -t target -S -200`.
- For continuous monitoring, poll with the helper script (below) instead of `tmux wait-for` (which does not watch pane output).
- You can also temporarily attach to observe: `tmux -L "$SOCKET" attach -t "$SESSION"`; detach with `Ctrl+b d`.
- When giving instructions to a user, **explicitly print a copy/paste monitor command** alongside the action don't assume they remembered the command.
## Spawning Processes
Some special rules for processes:
- when asked to debug, use lldb by default
- when starting a python interactive shell, always set the `PYTHON_BASIC_REPL=1` environment variable. This is very important as the non-basic console interferes with your send-keys.
## Synchronizing / waiting for prompts
- Use timed polling to avoid races with interactive tools. Example: wait for a Python prompt before sending code:
```bash
./scripts/wait-for-text.sh -t "$SESSION":0.0 -p '^>>>' -T 15 -l 4000
```
- For long-running commands, poll for completion text (`"Type quit to exit"`, `"Program exited"`, etc.) before proceeding.
## Interactive tool recipes
- **Python REPL**: `tmux ... send-keys -- 'python3 -q' Enter`; wait for `^>>>`; send code with `-l`; interrupt with `C-c`. Always with `PYTHON_BASIC_REPL`.
- **gdb**: `tmux ... send-keys -- 'gdb --quiet ./a.out' Enter`; disable paging `tmux ... send-keys -- 'set pagination off' Enter`; break with `C-c`; issue `bt`, `info locals`, etc.; exit via `quit` then confirm `y`.
- **Other TTY apps** (ipdb, psql, mysql, node, bash): same pattern—start the program, poll for its prompt, then send literal text and Enter.
## Cleanup
- Kill a session when done: `tmux -S "$SOCKET" kill-session -t "$SESSION"`.
- Kill all sessions on a socket: `tmux -S "$SOCKET" list-sessions -F '#{session_name}' | xargs -r -n1 tmux -S "$SOCKET" kill-session -t`.
- Remove everything on the private socket: `tmux -S "$SOCKET" kill-server`.
## Helper: wait-for-text.sh
`./scripts/wait-for-text.sh` polls a pane for a regex (or fixed string) with a timeout. Works on Linux/macOS with bash + tmux + grep.
```bash
./scripts/wait-for-text.sh -t session:0.0 -p 'pattern' [-F] [-T 20] [-i 0.5] [-l 2000]
```
- `-t`/`--target` pane target (required)
- `-p`/`--pattern` regex to match (required); add `-F` for fixed string
- `-T` timeout seconds (integer, default 15)
- `-i` poll interval seconds (default 0.5)
- `-l` history lines to search from the pane (integer, default 1000)
- Exits 0 on first match, 1 on timeout. On failure prints the last captured text to stderr to aid debugging.Related Skills
running-interactive-commands-with-tmux
Controls interactive CLI tools (vim, git rebase -i, REPLs) through tmux detached sessions and send-keys. Use when running tools requiring terminal interaction, programmatic editor control, or orchestrating Claude Code sessions. Triggers include "interactive command", "vim", "REPL", "tmux", or "git rebase -i".
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
moai-lang-r
R 4.4+ best practices with testthat 3.2, lintr 3.2, and data analysis patterns.
moai-lang-python
Python 3.13+ development specialist covering FastAPI, Django, async patterns, data science, testing with pytest, and modern Python features. Use when developing Python APIs, web applications, data pipelines, or writing tests.
moai-icons-vector
Vector icon libraries ecosystem guide covering 10+ major libraries with 200K+ icons, including React Icons (35K+), Lucide (1000+), Tabler Icons (5900+), Iconify (200K+), Heroicons, Phosphor, and Radix Icons with implementation patterns, decision trees, and best practices.
moai-foundation-trust
Complete TRUST 4 principles guide covering Test First, Readable, Unified, Secured. Validation methods, enterprise quality gates, metrics, and November 2025 standards. Enterprise v4.0 with 50+ software quality standards references.
moai-foundation-memory
Persistent memory across sessions using MCP Memory Server for user preferences, project context, and learned patterns
moai-foundation-core
MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows
moai-cc-claude-md
Authoring CLAUDE.md Project Instructions. Design project-specific AI guidance, document workflows, define architecture patterns. Use when creating CLAUDE.md files for projects, documenting team standards, or establishing AI collaboration guidelines.
moai-alfred-language-detection
Auto-detects project language and framework from package.json, pyproject.toml, etc.
mnemonic
Unified memory system - aggregates communications and AI sessions across all channels into searchable, analyzable memory
mlops
MLflow, model versioning, experiment tracking, model registry, and production ML systems