Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill replaces single-pass security reviews with a structured generate-judge-verify methodology. It is designed for security researchers conducting deep-dive audits of repositories, services, or modules where maximum coverage and adversarial verification are required to find exploitable bugs.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Installs: The raptor-loop-hunt repository cloned as a personal Claude Code skill. · Claude Code
Before you start
Claude Code
Git
In a terminal, clone the repository into the documented Claude Code personal-skills location. Start a new Claude Code session afterward so the skill is discovered automatically.
Replace <path-to-module> with the path to a repository module or directory containing the source code to audit.
Use the raptor-loop-hunt skill to audit <path-to-module> for security vulnerabilities. Apply its inventory-first generate-judge-verify methodology and report findings that were verified against the source.