tmux

Low
by steipete | Audited: 2026-02-26T09:59:20.936Z | Ruleset: 0.2.0

Quick Install

Add this skill to your agent

clawhub install tmux

About This Skill

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Use CLAWDBOT_TMUX_SOCKET_DIR (default ${TMPDIR:-/tmp}/clawdbot-tmux-sockets).
Default socket path: "$CLAWDBOT_TMUX_SOCKET_DIR/clawdbot.sock".
Target format: session:window.pane (defaults to :0.0).
Keep names short; avoid spaces.
Inspect: tmux -S "$SOCKET" list-sessions, tmux -S "$SOCKET" list-panes -a.
List sessions on your socket: {baseDir}/scripts/find-sessions.sh -S "$SOCKET".
Scan all sockets: {baseDir}/scripts/find-sessions.sh --all (uses CLAWDBOT_TMUX_SOCKET_DIR).
Prefer literal sends: tmux -S "$SOCKET" send-keys -t target -l -- "$cmd".

Use Cases

1 Workflow automation
2 Data transformation
3 System integration

Documentation (Original)

Source: SKILL.md
The following is the author's original documentation (often English). For installation, follow “Quick Install” above.

name: tmux
description: Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
metadata: {"clawdbot":{"emoji":"🧵","os":["darwin","linux"],"requires":{"bins":["tmux"]}}}

tmux Skill (Clawdbot)

Use tmux only when you need an interactive TTY. Prefer bash background mode for long-running, non-interactive tasks.

Quickstart (isolated socket, bash tool)

SOCKET_DIR="${CLAWDBOT_TMUX_SOCKET_DIR:-${TMPDIR:-/tmp}/clawdbot-tmux-sockets}"
mkdir -p "$SOCKET_DIR"
SOCKET="$SOCKET_DIR/clawdbot.sock"
SESSION=clawdbot-python

tmux -S "$SOCKET" new -d -s "$SESSION" -n shell
tmux -S "$SOCKET" send-keys -t "$SESSION":0.0 -- 'PYTHON_BASIC_REPL=1 python3 -q' Enter
tmux -S "$SOCKET" capture-pane -p -J -t "$SESSION":0.0 -S -200

After starting a session, always print monitor commands:

To monitor:
  tmux -S "$SOCKET" attach -t "$SESSION"
  tmux -S "$SOCKET" capture-pane -p -J -t "$SESSION":0.0 -S -200

Socket convention

  • Use CLAWDBOT_TMUX_SOCKET_DIR (default ${TMPDIR:-/tmp}/clawdbot-tmux-sockets).
  • Default socket path: "$CLAWDBOT_TMUX_SOCKET_DIR/clawdbot.sock".

Targeting panes and naming

  • Target format: session:window.pane (defaults to :0.0).
  • Keep names short; avoid spaces.
  • Inspect: tmux -S "$SOCKET" list-sessions, tmux -S "$SOCKET" list-panes -a.

Finding sessions

  • List sessions on your socket: {baseDir}/scripts/find-sessions.sh -S "$SOCKET".
  • Scan all sockets: {baseDir}/scripts/find-sessions.sh --all (uses CLAWDBOT_TMUX_SOCKET_DIR).

Sending input safely

  • Prefer literal sends: tmux -S "$SOCKET" send-keys -t target -l -- "$cmd".
  • Control keys: tmux -S "$SOCKET" send-keys -t target C-c.

Watching output

  • Capture recent history: tmux -S "$SOCKET" capture-pane -p -J -t target -S -200.
  • Wait for prompts: {baseDir}/scripts/wait-for-text.sh -t session:0.0 -p 'pattern'.
  • Attaching is OK; detach with Ctrl+b d.

Spawning processes

  • For python REPLs, set PYTHON_BASIC_REPL=1 (non-basic REPL breaks send-keys flows).

Windows / WSL

  • tmux is supported on macOS/Linux. On Windows, use WSL and install tmux inside WSL.
  • This skill is gated to darwin/linux and requires tmux on PATH.

Orchestrating Coding Agents (Codex, Claude Code)

tmux excels at running multiple coding agents in parallel:

SOCKET="${TMPDIR:-/tmp}/codex-army.sock"

# Create multiple sessions
for i in 1 2 3 4 5; do
  tmux -S "$SOCKET" new-session -d -s "agent-$i"
done

# Launch agents in different workdirs
tmux -S "$SOCKET" send-keys -t agent-1 "cd /tmp/project1 && codex --yolo 'Fix bug X'" Enter
tmux -S "$SOCKET" send-keys -t agent-2 "cd /tmp/project2 && codex --yolo 'Fix bug Y'" Enter

# Poll for completion (check if prompt returned)
for sess in agent-1 agent-2; do
  if tmux -S "$SOCKET" capture-pane -p -t "$sess" -S -3 | grep -q "❯"; then
    echo "$sess: DONE"
  else
    echo "$sess: Running..."
  fi
done

# Get full output from completed session
tmux -S "$SOCKET" capture-pane -p -t agent-1 -S -500

Tips:

  • Use separate git worktrees for parallel fixes (no branch conflicts)
  • pnpm install first before running codex in fresh clones
  • Check for shell prompt ( or $) to detect completion
  • Codex needs --yolo or --full-auto for non-interactive fixes

Cleanup

  • Kill a session: 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

{baseDir}/scripts/wait-for-text.sh polls a pane for a regex (or fixed string) with a timeout.

{baseDir}/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 (integer, default 1000)

Security Audit

Low

Summary

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Risk Profile Toxicity Privacy Scope Reputation Quality

ToxicSkills Analysis

Blocklist
Not matched
Prompt Injection
Not detected

No Toxic signals detected by current static checks.

Key Risks 0 items

No LLM risk bullets (LLM disabled or not cached).

Deterministic Findings (Evidence)

No findings detected.

Scoring Criteria

Each skill is scored across 5 dimensions. The weighted total determines the star rating.

Code Toxicity 100/100 (weight 30%)
Privacy Risk 100/100 (weight 25%)
Permission Scope 100/100 (weight 20%)
Author Reputation 75/100 (weight 15%)
Code Quality 70/100 (weight 10%)

Star Rating Scale

5★ Safe — Score ≥ 80
4★ Good — Score 70–79
3★ Caution — Score 60–69
2★ Risky — Score 40–59
1★ Dangerous — Score < 40

Why This Score?

All dimensions scored above 60. This skill passed the safety baseline.

Explore More Skills

VettedSkillsHub

We curate the top 100 most downloaded skills from ClawHub — the official ClawdBot (OpenClaw) marketplace — then run independent 5-dimension security audits. Transparent evidence, reproducible scores, 1-click install.

About

Best-effort static analysis. Scores are reproducible and evidence-based. Always review code and run in isolated environments for sensitive use.

© 2026 VettedSkillsHub. ClawdBot & OpenClaw are community projects.