Explore, design, and review a feature with specialist agents.
agentsAnthropic repository149,376 repo starsRepo updated Oct 3, 2026
Security Review Agents
Structure code security reviews and threat-model discussions with dedicated agent definitions.
security
About Security Review Agents
Security Scanning pairs an audit-oriented role with a threat modeling specialist. It can help identify trust boundaries, review authentication flows and organize potential weaknesses for investigation. The package is an instruction workflow rather than a certified scanner; findings need concrete evidence and validation in the application’s actual context.
- Security auditor and threat modeling definitions in one package.
- Distributed as the security-scanning plugin in the Claude Code Workflows marketplace.
How to install
Open the source documentation to check prerequisites and installation scope. Copy the commands below and run them one line at a time. Replace any example paths with the directory you intend to use.
Terminal
claude plugin marketplace add wshobson/agents
claude plugin install security-scanning@claude-code-workflowsComplete any authentication or settings steps documented by the maintainer, then reload the session and confirm the capability is available. Entries in the same repository may share a parent plugin installation.
Getting started
Provide the architecture, relevant code and trust assumptions. Request reproducible evidence and distinguish confirmed issues from hypotheses. Install this named workflow package, then check its available roles in /agents.
Before you use it
Review the project instructions and requested tool access, then try a small task. This directory checks sources and setup notes; inclusion is not a code security audit.