How do I install the Openclaw Guardian skill?

Run npx skillmds@latest add leoyeai-openclaw-master-skills/openclaw-guardian 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.

Is Openclaw Guardian safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openclaw Guardian?

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.

Is Openclaw Guardian free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Openclaw Guardian?

LeoYeAI (@leoyeai-openclaw-master-skills) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Openclaw Guardian by leoyeai-openclaw-master-skills

Name: Openclaw Guardian
Rating: 4.5 (4 reviews)
Author: LeoYeAI

Openclaw Guardian

Deploy and manage a Guardian watchdog process for OpenClaw Gateway. Provides automated health monitoring, self-repair via `doctor --fix`, git-based workspace rollback, daily snapshots, and optional Discord alerting. Use when a user wants to harden their OpenClaw instance against crashes, config corruption, or bad workspace edits — or when setting up Guardian for the first time on a new server/container.

LeoYeAI Updated Sep 10, 2026

File contents

OpenClaw Guardian

Guardian is a standalone bash watchdog that keeps OpenClaw Gateway alive 24/7.

Repair ladder:

Detect Gateway down (every 30s)
Run openclaw doctor --fix (up to 3 attempts)
If still down → git reset --hard to last stable commit, restart Gateway
If all fails → cooldown 300s, resume monitoring
Daily automatic git snapshot of workspace

Setup Steps

1. Initialize git (required for rollback)

cd ~/.openclaw/workspace
git config --global user.email "guardian@example.com"
git config --global user.name "Guardian"
git init && git add -A && git commit -m "initial"

Skip if repo already exists. Without git, doctor --fix still works; rollback is skipped.

2. Install guardian.sh

Copy scripts/guardian.sh from this skill to ~/.openclaw/guardian.sh:

cp scripts/guardian.sh ~/.openclaw/guardian.sh
chmod +x ~/.openclaw/guardian.sh

3. Start Guardian

Container / no systemd (nohup):

nohup ~/.openclaw/guardian.sh >> /tmp/openclaw-guardian.log 2>&1 &

Linux VPS with systemd: See references/setup.md → Pattern B.

4. Auto-start on container restart

Add to ~/.openclaw/start-gateway.sh (before the final exec line):

pkill -f "guardian.sh" 2>/dev/null || true
nohup /home/ubuntu/.openclaw/guardian.sh >> /tmp/openclaw-guardian.log 2>&1 &

5. Optional: Discord alerts

export DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."

Or add to start-gateway.sh as a persistent export.

Verify

pgrep -a -f "guardian.sh"          # confirm process running
tail -f /tmp/openclaw-guardian.log  # watch live logs

Configuration

All settings via environment variables. Defaults work out of the box. See references/setup.md for full variable reference, systemd config, and architecture diagram.

Notes

Guardian coexists with gw-watchdog.sh — run both for layered resilience
Rollback targets the 2nd-newest non-auto commit (skips daily-backup, rollback, auto-backup commits)
Log path: /tmp/openclaw-guardian.log

---name: openclaw-guardiandescription: Deploy and manage a Guardian watchdog process for OpenClaw Gateway. Provides automated health monitoring, self-repair via `doctor --fix`, git-based workspace rollback, daily snapshots, and optional Discord alerting. Use when a user wants to harden their OpenClaw instance against crashes, config corruption, or bad workspace edits — or when setting up Guardian for the first time on a new server/container.---# OpenClaw GuardianGuardian is a standalone bash watchdog that keeps OpenClaw Gateway alive 24/7.**Repair ladder:**1. Detect Gateway down (every 30s)2. Run `openclaw doctor --fix` (up to 3 attempts)3. If still down → `git reset --hard` to last stable commit, restart Gateway4. If all fails → cooldown 300s, resume monitoring5. Daily automatic git snapshot of workspace## Setup Steps### 1. Initialize git (required for rollback)```bashcd ~/.openclaw/workspacegit config --global user.email "guardian@example.com"git config --global user.name "Guardian"git init && git add -A && git commit -m "initial"```Skip if repo already exists. Without git, doctor --fix still works; rollback is skipped.### 2. Install guardian.shCopy `scripts/guardian.sh` from this skill to `~/.openclaw/guardian.sh`:```bashcp scripts/guardian.sh ~/.openclaw/guardian.shchmod +x ~/.openclaw/guardian.sh```### 3. Start Guardian**Container / no systemd (nohup):**```bashnohup ~/.openclaw/guardian.sh >> /tmp/openclaw-guardian.log 2>&1 &```**Linux VPS with systemd:** See `references/setup.md` → Pattern B.### 4. Auto-start on container restartAdd to `~/.openclaw/start-gateway.sh` (before the final `exec` line):```bashpkill -f "guardian.sh" 2>/dev/null || truenohup /home/ubuntu/.openclaw/guardian.sh >> /tmp/openclaw-guardian.log 2>&1 &```### 5. Optional: Discord alerts```bashexport DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."```Or add to `start-gateway.sh` as a persistent export.## Verify```bashpgrep -a -f "guardian.sh" # confirm process runningtail -f /tmp/openclaw-guardian.log # watch live logs```## ConfigurationAll settings via environment variables. Defaults work out of the box.See `references/setup.md` for full variable reference, systemd config, and architecture diagram.## Notes- Guardian coexists with `gw-watchdog.sh` — run both for layered resilience- Rollback targets the 2nd-newest non-auto commit (skips daily-backup, rollback, auto-backup commits)- Log path: `/tmp/openclaw-guardian.log`

Frequently asked questions