code-reviewer

Analyze code diffs with read-only tools to report gaps, risks, and compliance issues.

Updated Mar 10, 2026

Search Tags:#ai-agent #code-review #read-only #diff-analysis #structured-report #workflow-integration #adversarial-review

Ready to run

npx skills add https://github.com/iamsteveholmes/momentum --skill code-reviewer-iamsteveholmes

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: code-reviewer
Source: https://github.com/iamsteveholmes/momentum/tree/main/skills/momentum/skills/code-reviewer
Command: npx skills add https://github.com/iamsteveholmes/momentum --skill code-reviewer-iamsteveholmes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Adversarial code reviewer with read-only tools. Produces structured findings reports. Invoked by VFL — do not invoke directly.

Core Features & Use Cases

Read-only evaluation of diffs and files to surface potential issues.
Generates structured findings with severity, rationale, and mitigations.
Use Case: Integrate into pull requests to obtain an independent diagnostic before merge.

Quick Start

Start a review against a target diff to obtain a concise, structured findings report.

Frequently Asked Questions about code-reviewer

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

FAQPage Schema

How do I perform an automated code review on a pull request diff?▼

Automated code review evaluates pull request diffs to identify security risks, quality issues, and maintainability gaps. It analyzes code changes using read-only tools to produce structured findings with severity levels, rationale, and mitigations before merging.

What is an adversarial code review and when do I need it?▼

Adversarial code review critically evaluates diffs to surface gaps, risks, and compliance issues. It is needed during pull requests and pre-merge workflows to obtain an independent diagnostic of code changes across repositories, languages, and frameworks.

How do I get structured code review findings with severity and mitigations?▼

To get structured code review findings, analyze diffs using read-only tooling to evaluate security and quality. This generates a concise report detailing each issue's severity, rationale, and suggested mitigations for pre-merge integration.

Can I use a read-only code reviewer for pre-merge pull request validation?▼

Yes, a read-only code reviewer can be used for pre-merge pull request validation. It strictly evaluates diffs and files without modifying code, focusing on security, quality, maintainability, and compliance issues across repositories and frameworks.

What is the best way to integrate diagnostic code analysis into a pre-merge workflow?▼

The best way to integrate diagnostic code analysis into a pre-merge workflow is using an orchestrating system to invoke a read-only reviewer. This surfaces security, quality, and compliance risks in diffs, producing structured findings before code merges.

What are the limitations of using a read-only adversarial code reviewer?▼

A read-only adversarial code reviewer only analyzes diffs and files without applying fixes. It is orchestrated by specific workflows and cannot be invoked directly, focusing solely on reporting gaps, risks, and compliance issues across repositories and frameworks.