Anthropic's Claude Security now scans continuously. You connect your repositories once, Claude runs a deep baseline scan, then keeps checking new commits for vulnerabilities, with no scheduling. It is in public beta on Claude Enterprise.
What it does
- Baseline scan: a deep first pass over each connected repository. It can take minutes or hours and you can leave the page.
- Rescans: Claude checks for new commits and keeps scanning. You pick the branch and scope per repository.
- Fix tracking: an open finding is marked fixed when a fix lands, and it reopens if Claude detects the issue again.
- Every finding comes with confidence, severity, likely impact, reproduction steps and targeted patch instructions. Export as CSV or Markdown, or send to Slack and Jira with webhooks.
Free, for your email
Get the full setup steps + the copy-paste setup prompt
The rest of this guide (4 more sections) opens right here. The setup prompt, one paste into Claude that sets it all up, comes by email only. Use your real address.
50,000+ follow where these guides come from. No spam, unsubscribe in one click.