onex-hostile-reviewer

Run adversarial code reviews on pull requests using multiple models.

2|2|Updated Mar 28, 2026

Search Tags:#static analysis #code review #multi-model #risk assessment #adversarial review

Ready to run

npx skills add https://github.com/Julian0444/omnicursor --skill onex-hostile-reviewer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: onex-hostile-reviewer
Source: https://github.com/Julian0444/omnicursor/tree/main/.cursor/skills/onex-hostile-reviewer
Command: npx skills add https://github.com/Julian0444/omnicursor --skill onex-hostile-reviewer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires omniintelligence, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of accurately identifying and mitigating code-related risks in a software development process.

Core Features & Use Cases

Adversarial Review: Combines multiple code review models to cross-check findings for higher accuracy.
Static Analysis: Performs code quality checks without the need for adversarial multi-model review.
PR and File Review: Offers both PR and file review modes to cater to different code review scenarios.
Merge Gate: Provides a merge gate mode that runs parallel review agents for scope, correctness, and conventions.

Quick Start

Run the onex-hostile-reviewer skill to review a pull request using:

/hostile-reviewer --pr <N> --repo <owner/repo>

Frequently Asked Questions about onex-hostile-reviewer

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

FAQPage Schema

How does multi-model adversarial code review improve risk assessment?▼

Multi-model adversarial code review improves risk assessment by utilizing multiple models like Codex and DeepSeek-R1 to cross-check findings, which increases the accuracy of identifying and mitigating code-related risks.

How do I run an adversarial review on a pull request?▼

To run an adversarial review on a pull request, execute the hostile-reviewer command with the specific PR number and repository, such as /hostile-reviewer --pr <N> --repo <owner/repo>, to initiate the multi-model analysis.

Do I need the omniintelligence library to use this static analysis and merge gate functionality?▼

Yes, you need the omniintelligence review pairing library to perform adversarial code reviews and enable merge gate modes that run parallel review agents for scope, correctness, and conventions.

What is the difference between static analysis and adversarial review in code quality checks?▼

Static analysis performs standard code quality checks, while adversarial review combines multiple models to cross-check findings for higher accuracy in risk assessment during PR, file, or merge gate scenarios.

Can I use this tool for file reviews instead of full pull requests?▼

Yes, the tool offers both PR and file review modes to cater to different code review scenarios, allowing you to perform multi-model adversarial risk assessment on individual files.

What does the merge gate mode do for code review?▼

Merge gate mode runs parallel review agents to evaluate code for scope, correctness, and conventions, providing an automated gate that ensures high-quality risk assessment before merging changes.