According to Claude (@claudeai) on X, Anthropic introduced Claude Code Security in a limited research preview that scans codebases for vulnerabilities and proposes targeted patches for human review. According to Anthropic’s announcement page linked in the post, the system aims to catch issues traditional static analysis tools often miss and streamlines remediation by producing patch suggestions developers can audit and apply. As reported by the official Claude account, early positioning emphasizes developer-in-the-loop security workflows, suggesting business impact in reduced mean time to remediate and broader coverage across large repositories.