AI-Powered Code Defect Detection for Multi-Language Repos

AI-Powered Code Defect Detection for Multi-Language Repos

This AI agent skill audits code changes for defects before release. It operates on Git repositories and examines specific branches or pull requests to identify potential quality issues in the codebase. The skill is designed to detect defects in multiple programming languages, including Java, Kotlin, Scala, JavaScript, TypeScript, Python, Go, C, C++, and C#.

What this skill does

• Clones the specified Git repository and identifies differences between the target branch and the base branch.
• Extracts and analyzes changed methods using static rules and language-specific guidelines.
• Cross-checks against requirements, test cases, and known defects to identify any discrepancies or risks.
• Generates findings with line numbers and provides fix suggestions.
• Offers an HTML report summarizing the identified defects.
• Supports optional overlays like secret detection, software composition analysis, and native analyzer findings.
• Operates in two modes: 'light' for less than 200 line changes, and 'strict' for 200 or more line changes.

Who it is for

• Developers and development teams seeking automated defect detection in their code repositories.
• Quality assurance professionals who require an additional tool for code review processes.
• Teams using AI coding agents like Claude Code, Cursor, or Codex to streamline their code inspection workflows.

Use cases

• Identifying defects prior to code release in a Git branch or pull request.
• Reviewing code changes to assess possible change or regression risks.
• Resuming previously started defect detection tasks mid-process.
• Analyzing a test plan for potential issues or rechecking code prior to official release.

Technical details

• Leverages a combination of Semgrep seed packs and language-specific rules for effective defect identification.
• Utilizes method-by-method inspection driven by AI agents to ensure thorough analysis.
• Integrates with Git repositories for seamless inspection and reporting.

For authorised security testing, defensive research, and educational use only.

Source & Licence

This package is built on open-source work published by openqa-cn (openqa-cn/codexqa) and distributed under Apache-2.0. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted under the Apache License 2.0, which also includes an express patent grant. Attribution and any NOTICE file must be retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.