clelp-skills
by oscarsterling
A collection of installable skills, hooks and an MCP server for AI coding agents, made by the team behind the Clelp tool-rating site. It covers safety checks, cost control, secret protection and tool discovery for agents such as Claude Code.
- Stars
- 0
- Licence
- MIT
- Runs on
- Your computer
- Setup
- Moderate
- Language
- Python
- Age
- 122 days
What you can do with it
- Block secrets and credentials from leaving an agent, and refuse forged commands with guard hooks
- Cut model costs by keeping an expensive model on orchestration and auditing cron jobs that never needed an LLM
- Search and rate thousands of AI tools from your agent, or control Claude Code from your phone over Telegram
Make money with it
A freelancer could offer agent security reviews or cost-reduction audits for small teams using the review and audit tools here.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Reduce AI spending by routing code writing to cheaper models and replacing needless LLM cron jobs with local scripts
- Add security checks and secret protection to agent workflows that touch client data or databases
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Add it to Claude Code
claude mcp add clelp -- npx -y clelp-mcp-server
From the official MCP Registry (ai.clelp/clelp). Only connect MCP servers you trust: they can act on your behalf.
Getting it running
Each tool sits in its own directory with its own README; skills are copied into your agent's skills path, while the MCP server installs from npm and yburn from PyPI.
Follow the official instructions in the project README.
Things to check
- Some tools are very new, with listings still pending
- Each tool has its own licence file, so check them individually
- Some tools likely need access to several paid AI model providers
- Zero stars, so little community track record
Checked 02 Nov 2026. Summary drafted by AI from the project's README.
