Chasing Next
Explore LessonsAI UpdatesBlogAbout
Log inFor TeamsStart for Free
Chasing Next

Learn AI by doing.

Start for FreeFor TeamsAboutFAQUpdatesBlog
Sign UpSign InSupport
2026 Moonswell Marketing LLC·Terms·Privacy··
All Updates
AnthropicAnthropicfeature
July 22, 2026·Source

Claude Security Plugin for Claude Code (Beta)

A Claude Code plugin that scans your codebase for security vulnerabilities and drafts fixes you review, for developers on a paid Claude plan.

Details

  • Runs a team of Claude agents that map your architecture, build a threat model, hunt for vulnerabilities, and independently check each finding before it lands in the report
  • Adds one command, /claude-security, with three jobs: scan the whole codebase, scan just a branch or a single commit, or turn findings into patches
  • Scans run locally in your Claude Code session and count against your plan's usage limits, so the code never leaves your machine
  • Patches are drafted in a scratch copy of the repository and land in a patches folder for you to apply with git apply, never applied automatically
  • Needs Claude Code v2.1.154 or later on a paid plan, and reaches repositories the hosted Claude Security product cannot, including ones on GitLab, Bitbucket, or networks that block inbound connections

Best for

checking a repository or a branch's changes for security holes without handing the code to an outside scanning service

When to use it

before merging a branch, or on a codebase nobody has security-reviewed

Who benefits

developers, engineering leads, and non-engineers on paid Claude plans who work in Claude Code

More from Anthropic

All updates
feature
Claude Voice Mode (Upgraded)
feature
Claude Cowork Record a Skill
pricing
Fable 5 Added to Max and Team Premium Plans
Chasing Next

Staying informed is great. Staying ahead is better.

Pick a topic and leave with something you created.

Start for FreeBring to Your Team

Get new module drops and weekly AI strategy.