Without a playbook, asking an AI agent to "review my code for security" gives you a surface-level checklist. With these plays, the agent follows a structured OWASP-grounded procedure â systematically testing every vulnerability class, producing findings with CWE mappings, OpenCRE cross-references, evidence snippets, and specific remediation code. Consistent methodology â Every assessment follows a


{{#tags}}- {{label}}
{{/tags}}