AI Engineering Agent: Multi-Mode Code & Review Tool

AI Engineering Agent: Multi-Mode Code & Review Tool

The AI Engineering Agent: Multi-Mode Code & Review Tool is a platform-agnostic skill designed for AI coding agents like Claude Code, Cursor, and Codex. It provides a structured approach to code management and review through its three distinct modes: planning, building, and reviewing code changes.

What this skill does

• --plan: Proposes file changes for human approval and concurrently writes the per-feature todo tickets. This mode is invoked using the `--plan` flag and is detailed in the protocol found in `refs/plan/protocol.md`.
• --build: Constructs code according to the finalized build specifications documented in the todo tickets. When initiated, this mode spawns a reviewer subagent to perform a comprehensive review of the changes. The handling and routing are specified in `refs/build/protocol.md`.
• --review: Conducts an adversarial review of the working diff. This review can be initiated standalone at any time on any branch or is automatically triggered by the build subagent. Its protocol is detailed in `refs/review/protocol.md`.

Who it is for

This skill is intended for developers and engineering teams utilizing AI coding agents like Claude Code, Cursor, and Codex. It supports those who require a streamlined workflow for planning, building, and reviewing code across multiple platforms.

Use cases

• Developers seeking an organized method for planning and tracking code changes by generating todo tickets.
• Engineering teams automating their build processes while ensuring that specifications are adhered to accurately.
• Teams focusing on quality assurance through thorough code review adversarial checks prior to code integration.

Technical details

The AI Engineering Agent operates through specific protocol files segmented according to function. The core operational instructions are within `refs/protocol-core.md`, which dictates the primary sequential steps. Each mode loads its respective protocol file according to the invocation flag used. The system is platform-agnostic and integrates seamlessly with AI coding agents, contributing to a robust and efficient development environment.

Source & Licence

This package is built on open-source work published by ndisisnd (ndisisnd/msg) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are 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.