315 Claude Code plugins · 382 MCP servers · refreshed 26 Oct 2026Get your plugin featured →

claude-security

Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the verification tally computed in code. Turns surviving findings into targeted patches, each verified by a panel of agents, that you apply when you choose.

pluginupdated 26 Oct 2026by Anthropic
paste into Claude Code
/plugin install claude-security@claude-plugins-official

How to start

  1. Paste the command into Claude Code and press Enter.
  2. Restart Claude Code so the plugin loads.
  3. Just ask Claude. Its skills step in when your request fits.

What it adds

9 agents · 1 skill · 4 hooks

Agents Claude hands work to these

  • claude-securityThe Claude Security orchestrator, for use only as the main agent of a session (claude --agent claude-security:claude-security), where it runs a scan end to end…
  • exploreRead-only code explorer that the plugin's other agents dispatch to map a codebase — locate files, trace how a flow is wired, find every caller of a symbol, ans…
  • patch-generatorImplements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct…
  • patch-verifierThe single verifier per fix round — reviews the workspace's staged diff against the finding, runs the tests, and states the three confidence claims a patch fil…
  • scan-inventoryRestricted read-only repository cartographer dispatched by the Claude Security scan workflow to partition the tree into components and account for every top-le…
  • scan-loaderRestricted read-only loader dispatched by the Claude Security scan workflow to return one JSON file from the run directory; not for direct invocation.
  • scan-redactorRestricted agent dispatched by the Claude Security scan jobs to replace the credential values in a finished scan's report files with [REDACTED]; not for direct…
  • scan-researcherRestricted read-only vulnerability researcher dispatched by the Claude Security scan workflow; not for direct invocation or general exploration.
  • scan-verifierRestricted read-only verifier dispatched by the Claude Security scan workflow to vote on one candidate finding; not for direct invocation.

Skills Claude loads these when the task fits

  • claude-securityClaude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or sugg…

Hooks Run on their own at these moments

  • UserPromptExpansionA Claude Code hook event.
  • PostToolUseAfter Claude uses a tool.
  • PostToolUseFailureA Claude Code hook event.
  • PermissionRequestA Claude Code hook event.

Read from the plugin's own files in anthropics/claude-plugins-official, 26 Oct 2026.

What it needs

No keys or settings: its files ask for none.