OpenClaw Superpowers
44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring. Your agent teaches itself new behaviors during conversation.
What is OpenClaw Superpowers?
OpenClaw Superpowers is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 44 plug-and-play skills for openclaw — self-modifying ai agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and mcp health monitoring. your agent teaches itself new ...
44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring. Your agent teaches itself new behaviors during conversation.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 44 plug-and-play skills for OpenClaw — self-modifying AI age
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx openclaw-superpowersConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use OpenClaw Superpowers
OpenClaw Superpowers is a collection of 56 plug-and-play skills for the OpenClaw AI agent framework, covering self-modification (the agent can write new skills during a conversation), cron-scheduled automation, defense-in-depth security guardrails, persistent memory via SQLite and knowledge graphs, multi-agent coordination, API spend tracking, and MCP health monitoring. Skills install in a single command and activate automatically in new sessions, enabling solo developers and teams to build self-improving autonomous agents without writing boilerplate orchestration code. The security layer specifically addresses prompt injection, malicious skill installs, and destructive action prevention.
Prerequisites
- OpenClaw agent framework installed (openclaw gateway must be runnable)
- Git to clone the skills repository
- Bash shell for running the install script
- An MCP-compatible client compatible with OpenClaw
- Internet access for installing community skills and Obsidian sync
Clone the superpowers repository into OpenClaw extensions
Download all 56 skills into the standard OpenClaw extensions directory. This location is where OpenClaw looks for installed skill packs.
git clone https://github.com/ArchieIndian/openclaw-superpowers ~/.openclaw/extensions/superpowersRun the installer
Execute the install script from the cloned directory. It symlinks all skills, creates state directories for stateful skills, and registers cron jobs in one step.
cd ~/.openclaw/extensions/superpowers && ./install.shRestart the OpenClaw gateway
Apply the installation by restarting the gateway process. New skills become eligible after the restart.
openclaw gateway restartVerify eligible skills
Check which skills are active and eligible for use in the current session. Skills are opt-in — the model decides when to use them based on context.
openclaw skills list --eligibleAdd mandatory behaviors to AGENTS.md
For skills you want enforced deterministically (e.g., security monitoring, memory hygiene), add rules to your project's AGENTS.md file. This is more reliable than relying solely on system prompts.
Start a new session and use skills
Begin a fresh OpenClaw session. The agent will now have access to all 56 skills including brainstorming, task checkpointing, cron scheduling, knowledge graphs, and self-modification (create-skill).
OpenClaw Superpowers Examples
Client configuration
Configure your MCP client to connect to the OpenClaw gateway with superpowers enabled.
{
"mcpServers": {
"openclaw-superpowers": {
"command": "npx",
"args": ["openclaw-superpowers"]
}
}
}Prompts to try
Activate specific OpenClaw Superpowers skills to automate agent tasks and management.
- "Create a new skill that automatically labels GitHub issues by component when I ask you to triage"
- "Schedule a daily cron job to check our API spend and alert if it exceeds $10"
- "Build a knowledge graph of all the entities mentioned in our last 10 project planning sessions"
- "Run the security skill to scan all recently installed skills for prompt injection patterns"
- "Check the health of all connected MCP servers and report any that are unreachable"Troubleshooting OpenClaw Superpowers
The install.sh script fails with permission denied
Make the script executable first with 'chmod +x ~/.openclaw/extensions/superpowers/install.sh', then re-run it. If creating symlinks fails, check that ~/.openclaw/extensions/ exists and your user has write access.
Skills are installed but 'openclaw skills list --eligible' shows none
Start a completely fresh session after restarting the gateway — skills are session-scoped at activation time. If the list is still empty, verify the symlinks were created correctly in ~/.openclaw/skills/ and that the AGENTS.md or system prompt references the superpowers extension.
Cron-scheduled skills are not running on schedule
Check that the install script successfully registered the cron jobs by running 'crontab -l'. If missing, manually re-run './install.sh' from the superpowers directory. Confirm that 'openclaw gateway' is running as a background process when the cron jobs fire.
Frequently Asked Questions about OpenClaw Superpowers
What is OpenClaw Superpowers?
OpenClaw Superpowers is a Model Context Protocol (MCP) server that 44 plug-and-play skills for openclaw — self-modifying ai agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and mcp health monitoring. your agent teaches itself new behaviors during conversation. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install OpenClaw Superpowers?
Follow the installation instructions on the OpenClaw Superpowers GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with OpenClaw Superpowers?
OpenClaw Superpowers works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is OpenClaw Superpowers free to use?
Yes, OpenClaw Superpowers is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
OpenClaw Superpowers Alternatives — Similar Coding Agents Servers
Looking for alternatives to OpenClaw Superpowers? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up OpenClaw Superpowers in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use OpenClaw Superpowers?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.