Costa Score
Policy checkpoint that audits and blocks risky agent actions
Multi-phase security audits with verified, machine-readable findings
A coding-agent skill from Cloudflare for running multi-phase security audits with independently verified, machine-readable findings. It is for developers and security teams that want an agent to focus on real risk and impact instead of flooding them with low-value warnings.
The skill guides an agent through structured audit phases and asks it to produce findings that can be verified and consumed by tooling. The video notes that it is designed to work within agent guardrails and to prioritize actual exploitability and business impact over cosmetic issues.
Open Source Grok Bot, copy any YouTube video, find anyone online.
Policy checkpoint that audits and blocks risky agent actions
Production-grade engineering skills for AI coding agents
Stop agents repeating expensive calls and re-reading the same files
Self-hosted Bitwarden-compatible password manager server
Independent audit for AI agents in under two minutes
Kubernetes security scanner that finds and fixes misconfigurations