Claw Sos
by @robertfarkash29-source
Install, run, and manage the SOS emergency recovery tool for OpenClaw instances. Use when (1) the bot stops responding on Telegram/Discord and needs diagnosi...
clawhub install claw-sosπ About This Skill
name: claw-sos description: Install, run, and manage the SOS emergency recovery tool for OpenClaw instances. Use when (1) the bot stops responding on Telegram/Discord and needs diagnosis or recovery, (2) you need to install SOS on a new or existing machine, (3) autofix, rollback, network check, or Telegram test is needed, (4) the user mentions "sos", "recovery", "bot is down", "not responding", or "emergency fix".
claw-sos
Emergency recovery tool for OpenClaw. Diagnoses and fixes unresponsive bots via SSH.
Install
The script is bundled at scripts/sos.sh. Install locally:
cp scripts/sos.sh /usr/local/bin/sos
chmod +x /usr/local/bin/sos
To install on a remote machine:
scp scripts/sos.sh root@:/usr/local/bin/sos
ssh root@ "chmod +x /usr/local/bin/sos"
Alternative β install from GitHub:
curl -fsSL https://raw.githubusercontent.com/clawsos/claw-sos/main/install.sh | bash
Usage
Interactive (human via SSH)
sos # whiptail arrow-key menu
Non-interactive (agent or cron)
sos auto # autofix: diagnose β doctor β restart β force β nuclear
sos net # network check only
sos tg # telegram test message
sos --version
sos --help
When the bot is down β decision tree
1. Run sos auto β handles 95% of cases automatically
2. If autofix fails β run sos net β if network is broken, fix DNS/internet first
3. If network is fine but bot still down β run sos tg β check Telegram delivery
4. If Telegram fails β check bot token validity
5. Last resort β sos menu option 9 (Nuclear) β kills everything and starts fresh
Menu Options
| # | Name | What it does | Safe? | |---|------|-------------|-------| | 1 | Check status | Gateway running, RAM, disk, version | β Read-only | | 2 | Restart | Graceful restart | β Safe | | 3 | Force kill | Kill process + restart | β οΈ Drops active sessions | | 4 | Rollback | Revert to previous version + config | β οΈ Downgrade | | 5 | View logs | Last 50 lines of gateway log | β Read-only | | 6 | Full diagnostic | RAM, disk, Telegram, sessions, process | β Read-only | | 7 | Backup config | Save config + version before changes | β Safe | | 8 | Self-test | Verify SOS script works | β Read-only | | 9 | Nuclear | Kill ALL openclaw processes, reload | π΄ Last resort | | 10 | Autofix | Escalating auto-repair | β οΈ May restart | | 11 | Network check | DNS, internet, Telegram API, Anthropic | β Read-only | | 12 | Telegram test | Send real test message | β Safe |
Autofix Escalation Order
1. Diagnose: process, RAM, disk
2. Clean RAM/disk if critical
3. openclaw doctor --fix
4. Graceful restart β wait 15s β check
5. Force kill + restart β wait 15s β check
6. Nuclear (kill all + reload)
Stops as soon as gateway is healthy.
Log Location
All actions logged to ~/.openclaw/backups/sos.log. Read this to understand what happened during recovery:
cat ~/.openclaw/backups/sos.log
Platform Support
Credentials
This skill uses no API keys or tokens of its own. It reads existing OpenClaw config to:
openclaw.json)No credentials are stored, transmitted, or required to install or run SOS.
Source
GitHub: https://github.com/clawsos/claw-sos
π‘ Examples
Interactive (human via SSH)
sos # whiptail arrow-key menu
Non-interactive (agent or cron)
sos auto # autofix: diagnose β doctor β restart β force β nuclear
sos net # network check only
sos tg # telegram test message
sos --version
sos --help
When the bot is down β decision tree
1. Run sos auto β handles 95% of cases automatically
2. If autofix fails β run sos net β if network is broken, fix DNS/internet first
3. If network is fine but bot still down β run sos tg β check Telegram delivery
4. If Telegram fails β check bot token validity
5. Last resort β sos menu option 9 (Nuclear) β kills everything and starts fresh