Judge

Run codex review on cross-file code changes with severity classification.

Updated Mar 18, 2026
One-click install
npx skills add https://github.com/Dinxeshh/agent-skills --skill judge-dinxeshh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Judge
Source: https://github.com/Dinxeshh/agent-skills/tree/main/skills/judge
Command: npx skills add https://github.com/Dinxeshh/agent-skills --skill judge-dinxeshh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Judge eliminates manual, inconsistent reviews by running codex review to catch bugs, security vulnerabilities, and intent mismatches before merging changes.

Core Features & Use Cases

  • Automated Severity Triage: Runs codex review per PR, commit, or pre-commit scope and labels findings as CRITICAL through INFO.
  • Consistency & Test Quality Checks: Cross-file pattern detection plus test quality scoring steer the next agent handoffs and flag maintenance risks.
  • Remediation Routing: Each finding pairs evidence with an intended agent (Builder, Sentinel, Zen, Radar) so fixes stay coordinated.
  • Use Case: Use Judge on React, Next.js, Express, TypeScript, Python, or Go diffs to verify intent alignment, null safety, and error handling before approval.

Quick Start

Ask Judge to run codex review on your PR with the appropriate mode so it returns severity-classified findings and remediation routes.

Frequently Asked Questions about Judge

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

FAQPage Schema
How do I automate cross-file code review for a React or Next.js PR?

Automated code review for React and Next.js PRs runs codex review to execute cross-file pattern detection, classifying correctness and security findings by severity. Judge automates this workflow, returning labeled results with remediation routes before merging changes.

What is intent alignment checking in TypeScript code changes?

Intent alignment checking in TypeScript verifies that code changes match original design goals by analyzing cross-file diffs for mismatches. Judge automates this detection, flagging null safety and error handling issues before code approval.

Does automated code review work with Python and Go commits?

Automated code review works with Python and Go commits by executing codex review with proper flags across commit scopes. Judge targets Python and Go code changes to verify consistency, detect bugs, and score test quality before approval.

How do I classify security vulnerabilities by severity during pre-commit review?

Classifying security vulnerabilities by severity during pre-commit review labels findings from CRITICAL through INFO. Judge automates this severity triage by running codex review on pre-commit scopes, pairing each vulnerability with evidence and remediation routing.

What is the best way to detect cross-file consistency issues in Express applications?

Detecting cross-file consistency issues in Express applications requires cross-file pattern detection to identify maintenance risks. Judge executes codex review on Express diffs, flagging consistency issues and scoring test quality to steer remediation agent handoffs.