SecPlusDev

Verified Security Sweep — Security skill for Claude Code

Security community

Claude skill for security reviews you can verify, hand over and resume: one zone at a time, every confirmed finding on its exact line with a failing test, every run recorded so the next one re-checks.

How to install Verified Security Sweep

This entry records only its repository, not the path inside it, so there is no exact command to give. Open SecPlusDev/verified-security-sweep and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Verified Security Sweep does

Alternatives in Security

Marketplace — Security-audited skills for Claude, Codex & Claude Code 247 ★
Cross-Pollinate Hex MCP Servers — Diff-driven audit: find real transferable changes across hex-line-mcp, hex-ssh-mcp, hex-graph-mcp 238 ★
Mobile Resume — Audit an unfinished mobile app, create a completion plan, then implement remaining work after approval 107 ★

README

Verified Security Sweep

[![CI](https://github.com/SecPlusDev/verified-security-sweep/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/SecPlusDev/verified-security-sweep/actions/workflows/ci.yml) [![Release](https://img.shields.io/github/v/release/SecPlusDev/verified-security-sweep?display_name=tag&color=2563eb)](https://github.com/SecPlusDev/verified-security-sweep/releases/latest) [![License: MIT](https://img.shields.io/badge/license-MIT-16a34a)](LICENSE) [![Python 3.9+](https://img.shields.io/badge/python-3.9%2B-3776ab?logo=python&logoColor=white)](plugin/skills/verified-security-sweep/scripts/) [![Dependencies: none](https://img.shields.io/badge/dependencies-none-6b7280)](plugin/skills/verified-security-sweep/scripts/) [![Claude skill](https://img.shields.io/badge/Claude-skill-d97706)](plugin/skills/verified-security-sweep/SKILL.md) [![Security policy](https://img.shields.io/badge/security-policy-dc2626)](SECURITY.md)

**A Claude skill for security reviews you can verify, hand over and resume: one zone at a time, every confirmed finding located on its exact line and reproduced by a failing test, every run recorded so the next one re-checks the last instead of starting from zero.**

Claude finds the defects; the skill makes each finding checkable, keeps the record, and gives the next review a starting point. It complements an audit and the project's own tests. The skill reports, reproduces and proposes; the fixes go through your normal change process.

Listed in the Claude directory: `claude plugin install verified-security-sweep@anthropic-plugin-directory`.

What it adds to Claude, measured

Same prompt, same code (a Django service with three planted access-control defects), same model (Opus), once without the skill and once with it. Both runs found al