command (string, required): shell command to run inside session claw.
Behavior:
Attach to tmux session claw (create it if missing: tmux new -s claw -d).
Send the command followed by Enter.
Capture the latest pane output.
Return the captured output to the agent.
SAFETY
DO NOT RUN:
sudo
rm (without explicit user approval)
reboot, shutdown, or destructive system-level commands
IF THE COMMAND CONTAINS ANY OF THE ABOVE:
ASK USER FOR CONFIRMATION BEFORE EXECUTING.
EXAMPLES
SAFE:
ls -la
bird read https://x.com/...
git status
DANGEROUS (ASK FIRST):
rm -rf ...
docker system prune -a
chmod -R ...
1---2name: skills-backup-claw-shell3description: "Skills Backup Claw Shell"4metadata:5 source: https://skillmd.com/skills/dvcrn/skills-backup-claw-shell6---78# claw-shell910ALWAYS USES TMUX SESSION `claw`.1112## PURPOSE1314- RUN SHELL COMMANDS INSIDE TMUX SESSION `claw`15- NEVER TOUCH ANY OTHER SESSION16- READ OUTPUT BACK TO THE AGENT1718## INTERFACE1920### Tool: `claw_shell_run`2122**Inputs:**2324- `command` (string, required): shell command to run inside session `claw`.2526**Behavior:**27281. Attach to tmux session `claw` (create it if missing: `tmux new -s claw -d`).292. Send the command followed by Enter.303. Capture the latest pane output.314. Return the captured output to the agent.3233## SAFETY3435- DO NOT RUN:36 - `sudo`37 - `rm` (without explicit user approval)38 - `reboot`, `shutdown`, or destructive system-level commands39- IF THE COMMAND CONTAINS ANY OF THE ABOVE:40 - ASK USER FOR CONFIRMATION BEFORE EXECUTING.4142## EXAMPLES4344- SAFE:45 - `ls -la`46 - `bird read https://x.com/...`47 - `git status`4849- DANGEROUS (ASK FIRST):50 - `rm -rf ...`51 - `docker system prune -a`52 - `chmod -R ...`
Run npx get-skill add dvcrn/skills-backup-claw-shell in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Skills Backup Claw Shell It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.