review

Spawn independent subagents to adversarially review local code diffs for bugs and security flaws.

5|Updated Jun 3, 2026
One-click install
npx skills add https://github.com/vinceferro/claude-kickoff --skill review-vinceferro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/vinceferro/claude-kickoff/tree/main/plugin/skills/review
Command: npx skills add https://github.com/vinceferro/claude-kickoff --skill review-vinceferro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the limitation of standard code reviews where agents often rubber-stamp changes; it provides an adversarial, local-compute-based review process that actively attempts to break code to uncover hidden bugs and security vulnerabilities.

Core Features & Use Cases

  • Adversarial Fan-out: Spawns independent subagents tasked specifically with breaking the code across dimensions like correctness, security, and regression risk.
  • Verification Loop: Enforces a strict refute-by-default policy where every finding must be verified against the actual code before being accepted.
  • Use Case: Before merging a sensitive authentication change or a complex feature, run this skill to ensure that multiple specialized agents have stress-tested the logic locally without requiring external CI services.

Quick Start

Run the review skill on the current unstaged diff to perform an adversarial check for security and correctness.

Frequently Asked Questions about 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 local diff?

Run the review skill on your unstaged diff to perform an adversarial check. It spawns independent subagents that actively attempt to break code across correctness, security, and regression risk dimensions.

What is adversarial code review and how does it find security flaws?

Adversarial code review enforces a refute-by-default policy where independent subagents actively try to break code. Every finding is verified against the actual code locally before acceptance to uncover hidden bugs and security vulnerabilities.

When should I use an automated adversarial review instead of standard code review?

Use adversarial review before merging substantial code changes, security-sensitive logic, or irreversible operations. Standard reviews often rubber-stamp changes, whereas this approach actively attempts to break code to ensure robust quality control.

Does the review skill require external CI services to verify findings?

No, the review skill does not require external CI services. It uses local compute to execute parallel verification of findings, spawning subagents that verify every potential bug or security flaw against the actual code.

What types of code changes are best suited for local adversarial review?

Local adversarial review targets substantial code changes, security-sensitive authentication logic, and irreversible operations. It ensures multiple specialized agents have stress-tested the logic for correctness and regression risk before merging.