Ghost Scan Secrets

This is a proper secrets scanner that actually does multi-stage analysis instead of just regex matching. It uses an orchestrator pattern to spawn subagents that run a tool called Poltergeist against your codebase, then individually assess each candidate to cut down false positives. The findings get written to a structured directory under ~/.ghost with severity ratings and remediation guidance. It's built for when you need to audit a repo for leaked API keys, hardcoded passwords, or exposed .env values before they hit production. The agent architecture means it can parallelize analysis across candidates, which matters if you're scanning a large codebase. Outputs are organized by repo and commit hash, so you can track findings over time.

Install to Claude Code

npx -y skills add ghostsecurity/skills --skill ghost-scan-secrets --agent claude-code