Automated deployment, rollback, and version management for AI agent workflows and skills.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install arc-skill-gitops
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install arc-skill-gitops using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Agent GitOps provides a professional-grade DevOps workflow for managing Openclaw Skills. As AI agents frequently update or modify their own capabilities, the risk of breaking changes increases. This skill mitigates that risk by implementing a Git-based tracking system that records every state change, allowing for seamless rollbacks and stable versioning of your agent logic. It ensures that every modification to your Openclaw Skills is tracked, reversible, and verifiable.
To get started with Agent GitOps for your Openclaw Skills, ensure you have python3 and git installed on your system. Run the following commands:
# Initialize tracking for a specific skill
python3 {baseDir}/scripts/gitops.py init --skill ~/.openclaw/skills/my-skill/
# Snapshot the state before a major change
python3 {baseDir}/scripts/gitops.py snapshot --skill ~/.openclaw/skills/my-skill/ --tag "stable-v1"
# Check the status of all tracked skills
python3 {baseDir}/scripts/gitops.py status
Agent GitOps manages data through a combination of local git repositories and a centralized manifest:
| Component | Location/Format | Description |
|---|---|---|
| Metadata Store | ~/.openclaw/gitops/ | Stores the global tracking manifest for all Openclaw Skills. |
| Skill Repositories | ~/.openclaw/skills/[skill-name]/ | Contains the actual git history for the specific skill. |
| Snapshots | Git Tags | Named markers for specific versions like v1.1 or pre-update. |
Loading
A specialized security utility to compare different versions of Openclaw Skills and detect new, potentially dangerous capabilities before updating.

A high-fidelity security intelligence service providing real-time auditing, static analysis, and semantic threat detection for the AI agent ecosystem.

A unified security assessment tool that chains scanners and verifiers to harden and secure your entire agent skill ecosystem.

A lightweight operational monitoring tool to track agent health, API usage, and performance metrics through a text-based dashboard.

A proactive monitoring utility designed to track performance drift, error rates, and resource usage for deployed AI skills.

A comprehensive security auditing tool designed to detect credential stealers, data exfiltration, and malicious code within Openclaw Skills.








































