Ten gates that run before an AI agent workflow publishes anything: secrets scan with gitleaks, adversarial audit, license review, and a human doing the final push. Built so a dirty commit never leaves your machine. Ships as a Claude Code skill.
Cross-referenced across 55 tracked directories
#9048
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
7/16/2026
Created
1
GitHub Stars
8/2/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
LeonMelamud
AI-powered security audit skill for code changes with false positive filtering. Based on Anthropic's claude-code-security-review.
...morebenderterminal
Self-hosted, zero-knowledge encrypted, self-destructing secrets
agamm
Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, and 20+ language-specific security quirks.
...morewrsmith108
Claude Code skill for secure environment variable management with Varlock. Never expose secrets in Claude sessions.