Does it check for specific security vulnerabilities?

Yes, the security-reviewer agent is specifically designed to check for OWASP Top 10 vulnerabilities and provides confidence scores for each finding.

Can I use this for non-testing tasks?

This skill is specifically designed for tasks located in the review/ directory where comprehensive code quality and security verification are required before approval.

What triggers a code rejection in this skill?

Reviews are automatically rejected if the security score falls below 80, any tests fail, or if agents identify CRITICAL severity findings in security, errors, or test gaps.

Code Review Multi-Agent

Name: Code Review Multi-Agent
Author: dhruvbaldawa

bydhruvbaldawa

•

Security & Testing

Performs deep, parallel code reviews for security, performance, and test coverage using specialized AI agents.

About

This skill automates a rigorous code review process by deploying three specialized sub-agents—test coverage analyzer, error-handling reviewer, and security reviewer—in parallel to provide deep analysis. It moves beyond simple linting by verifying test execution, checking validation requirements, and scoring code across four key dimensions: Security, Quality, Performance, and Tests. This skill is essential for teams requiring high-standard security audits, robust error handling, and comprehensive test verification before merging code into production.

Key Features

3 GitHub stars
Test Suite Verification: Executes tests and analyzes coverage gaps with 1-10 criticality ratings.
Automated Approval Logic: Uses strict thresholds to approve or reject code based on criticality and confidence scores.
Parallel Agent Execution: Launches three specialized sub-agents simultaneously for faster, deeper analysis.
Comprehensive Scoring: Provides 0-100 scores for Security, Quality, Performance, and Tests to quantify code health.
Structured Reporting: Generates standardized approval or rejection notes including OWASP security findings.

Use Cases

Automated security auditing to identify OWASP vulnerabilities before code deployment.
Ensuring high test coverage and robust error handling in mission-critical software components.
Standardizing the code review workflow for teams using Claude Code for automated development tasks.

About

Key Features

3 GitHub stars
Test Suite Verification: Executes tests and analyzes coverage gaps with 1-10 criticality ratings.
Automated Approval Logic: Uses strict thresholds to approve or reject code based on criticality and confidence scores.
Parallel Agent Execution: Launches three specialized sub-agents simultaneously for faster, deeper analysis.
Comprehensive Scoring: Provides 0-100 scores for Security, Quality, Performance, and Tests to quantify code health.
Structured Reporting: Generates standardized approval or rejection notes including OWASP security findings.

Use Cases

Automated security auditing to identify OWASP vulnerabilities before code deployment.
Ensuring high test coverage and robust error handling in mission-critical software components.
Standardizing the code review workflow for teams using Claude Code for automated development tasks.