Agent Review

Spawn an independent agent to review code quality, security, and requirements.

Updated Jan 24, 2026

Search Tags:#testing #quality assurance #code review #security #agent #phase completion

Ready to run

npx skills add https://github.com/jdsingh122918/forge --skill agent-review-jdsingh122918

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Agent Review
Source: https://github.com/jdsingh122918/forge/tree/main/.forge/skills/agent-review
Command: npx skills add https://github.com/jdsingh122918/forge --skill agent-review-jdsingh122918

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill ensures that implementations are thoroughly checked for issues before a phase is considered complete, catching errors that the primary agent might have missed.

Core Features & Use Cases

Independent Verification: Spawns a separate agent to review code changes.
Issue Detection: Checks for DRY violations, security vulnerabilities, test coverage gaps, and code clarity.
Iterative Improvement: Facilitates addressing feedback and re-reviewing changes.
Use Case: After completing a complex coding phase, you can use this Skill to have an AI agent act as a second pair of eyes, reviewing the code for potential bugs or security flaws before proceeding.

Quick Start

Use the Task tool to spawn a review agent for phase N, providing the phase context and a checklist of review items.

Frequently Asked Questions about Agent Review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate code review for phase completion before moving to the next stage?▼

Automating code review for phase completion involves spawning an independent review agent that checks your implementation against quality, security, and requirement criteria. This verifies code changes iteratively before finalizing the phase.

What is an independent review agent and how does it detect security vulnerabilities?▼

An independent review agent is a separate AI instance that evaluates code changes for security vulnerabilities and DRY violations. It acts as a second pair of eyes to catch errors the primary agent missed during implementation.

How do I verify phase implementation requirements are met without manual inspection?▼

Verifying phase implementation requires spawning a review agent with your phase context and a checklist. The agent defines clear criteria for review success or failure, ensuring adherence to requirements without manual inspection.

What are the limitations of using an AI agent for quality assurance in software engineering?▼

Using an AI agent for quality assurance requires providing explicit phase context and review checklists. The agent's effectiveness depends on the defined criteria, and iterative feedback loops may be necessary to resolve complex issues.