adversarial-review

Orchestrate adversarial code reviews with opposing-model reviewers and synthesized verdicts.

1|Updated Mar 8, 2026

Search Tags:#multi-model #code-review #diff-analysis #adversarial-review #brain-principles #verdict-synthesis

Ready to run

npx skills add https://github.com/tense-i/stock-market-simulator --skill adversarial-review-tense-i

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: adversarial-review
Source: https://github.com/tense-i/stock-market-simulator/tree/main/.opencode/skill/adversarial-review
Command: npx skills add https://github.com/tense-i/stock-market-simulator --skill adversarial-review-tense-i

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. The deliverable is a synthesized verdict — do NOT make changes.

Core Features & Use Cases

Spawns reviewers on the opposite model to challenge work from distinct lenses grounded in brain principles.
Produces a synthesized verdict and a set of findings without applying changes automatically.
Handles multi-model orchestration, ensures parallel reviewer execution, and compiles the final lead judgment.

Quick Start

Initiate an adversarial review on the latest diffs to generate a verdict without applying changes.

Frequently Asked Questions about adversarial-review

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

FAQPage Schema

How do I run an adversarial code review on a large diff?▼

An adversarial code review deploys opposing-model reviewers to critically evaluate diffs from distinct lenses. The skill orchestrates parallel execution of these reviewers and compiles a synthesized verdict with findings and a lead judgment.

Can I use this to automatically apply changes after a multi-model review?▼

No, you cannot automatically apply changes after a multi-model review. The skill explicitly outputs a synthesized verdict and a set of findings without applying changes automatically, leaving the final modifications to the developer.

What is multi-model diff analysis and how does it work?▼

Multi-model diff analysis works by spawning reviewers on the opposing model, such as Claude spawning Codex, to challenge work. It enforces opposite-model execution to surface issues from multiple critical lenses and synthesizes a final verdict.

When should I use an adversarial review for my code changes?▼

You should use an adversarial review for large diffs, planning sessions, or complex changes. It is designed to surface issues from multiple critical lenses that a single reviewer might miss when evaluating extensive or intricate code modifications.

Does this review process require setting up dependencies for the opposing model?▼

No, setting up dependencies for the opposing model is not required. The skill manages multi-model orchestration internally, automatically handling the deployment of opposing models like Claude and Codex without external dependency configuration.