tmux
clawdbot
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
Quick Install
bunx add-skill clawdbot/clawdbot -s tmuxaiassistantcrustaceanmoltyopenclawown-your-data
Instructions
Loading…
clawdbot
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
bunx add-skill clawdbot/clawdbot -s tmuxLoading…
Use tmux only when you need an interactive TTY. Prefer exec background mode for long-running, non-interactive tasks.
SOCKET_DIR="${CLAWDBOT_TMUX_SOCKET_DIR:-${TMPDIR:-/tmp}/moltbot-tmux-sockets}"
mkdir -p "$SOCKET_DIR"
SOCKET="$SOCKET_DIR/moltbot.sock"
SESSION=moltbot-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
CLAWDBOT_TMUX_SOCKET_DIR (default ${TMPDIR:-/tmp}/moltbot-tmux-sockets)."$CLAWDBOT_TMUX_SOCKET_DIR/moltbot.sock".session:window.pane (defaults to :0.0).tmux -S "$SOCKET" list-sessions, tmux -S "$SOCKET" list-panes -a.{baseDir}/scripts/find-sessions.sh -S "$SOCKET".{baseDir}/scripts/find-sessions.sh --all (uses CLAWDBOT_TMUX_SOCKET_DIR).tmux -S "$SOCKET" send-keys -t target -l -- "$cmd".tmux -S "$SOCKET" send-keys -t target C-c.tmux -S "$SOCKET" capture-pane -p -J -t target -S -200.{baseDir}/scripts/wait-for-text.sh -t session:0.0 -p 'pattern'.Ctrl+b d.PYTHON_BASIC_REPL=1 (non-basic REPL breaks send-keys flows).darwin/linux and requires tmux on PATH.tmux excels at running multiple coding agents in parallel:
SOCKET="${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:
pnpm install first before running codex in fresh clones❯ or $) to detect completion--yolo or --full-auto for non-interactive fixestmux -S "$SOCKET" kill-session -t "$SESSION".tmux -S "$SOCKET" list-sessions -F '#{session_name}' | xargs -r -n1 tmux -S "$SOCKET" kill-session -t.tmux -S "$SOCKET" kill-server.{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)Use when you need to run Flow type checking, or when seeing Flow type errors in React code.
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.