🛡️ Mend
This skill automatically remediates known incident patterns by matching symptoms to remedies, performing safe fixes, and verifying recovery.
npx playbooks add skill simota/agent-skills --skill mend
About Mend
This skill automatically remediates known incident patterns by matching symptoms to remedies, performing safe fixes, and verifying recovery.
This compact 18-word instruction set is purpose-built for security work in AI coding agents. Install with a single command.
Use Cases
- Auditing code for OWASP Top 10 vulnerabilities
- Implementing authentication and authorization patterns
- Reviewing API security, rate limiting, and input validation
- Hardening infrastructure and dependency security
Example Prompts
System Prompt (18 words)
This skill automatically remediates known incident patterns by matching symptoms to remedies, performing safe fixes, and verifying recovery.
Frequently Asked Questions
What is Mend?
Mend is a free security skill for AI coding agents. This skill automatically remediates known incident patterns by matching symptoms to remedies, performing safe fixes, and verifying recovery.. It provides a specialized system prompt that configures your agent with security expertise.
How do I use Mend with Claude Code?
Run npx playbooks add skill simota/agent-skills --skill mend in your terminal to install Mend into your Claude Code session. It works immediately after installation.
Which AI coding agents work with Mend?
Mend is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Is Mend free to use?
Yes, Mend is completely free and open source. The full source is available on GitHub at https://github.com/simota/agent-skills/tree/main/mend. You only need a subscription to the AI agent you use it with.
