skills.rest
cegit27
cegit27OFFICIAL
Explore all skills by this author →
GitHub

codex

Automate code review, adversarial testing, and expert consultation via OpenAI Codex CLI.

3|14|Updated Mar 10, 2026
Search Tags:#code review#cli#codex#openai#adversarial testing#consult
One-click install
npx skills add https://github.com/cegit27/moodle-proctor --skill codex-cegit27
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: codex
Source: https://github.com/cegit27/moodle-proctor/tree/main/.claude/skills/gstack/codex
Command: npx skills add https://github.com/cegit27/moodle-proctor --skill codex-cegit27

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill wraps the OpenAI Codex CLI into three focused modes, eliminating the need to remember flags and manually chain commands for code review, adversarial testing, and expert consultation.

Core Features & Use Cases

  • Code Review: Get an independent pass/fail review of your code changes before merging.
  • Challenge Mode: Adversarially test your code to find breaking edge cases and security vulnerabilities.
  • Consult Mode: Ask Codex questions with session continuity for follow-up clarifications, like a senior engineer available on demand.
  • Use Case: Run a codex review on your feature branch to catch issues early, then use challenge mode to verify your error handling handles malicious inputs.

Quick Start

Use the codex skill to review the current git diff and report any issues that would fail the quality gate.

Frequently Asked Questions about codex

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

FAQPage Schema
How do I automate code review for my git diff before merging?▼

You can automate code review by running the Codex CLI in review mode to evaluate your git diff. This provides an independent pass/fail assessment to catch issues before merging.

What is adversarial testing and how does it find security vulnerabilities in my code?▼

Adversarial testing stress-tests your code with malicious inputs to find breaking edge cases and security vulnerabilities. This is done using the Codex CLI challenge mode to verify error handling and security boundaries.

Can I use the Codex CLI for expert consultation during feature development?▼

Yes, you can use the Codex CLI consult mode for expert consultation during feature development. It provides technical guidance with session continuity, allowing for follow-up clarifications like an on-demand senior engineer.

What tools and environment do I need to run Codex CLI commands?▼

Running Codex CLI commands requires Bash, Read, Write, Glob, Grep, and AskUserQuestion tool access. These tools are required to execute commands and manage session state for code review and testing workflows.

How do I check if my error handling handles malicious inputs correctly?▼

To check if your error handling handles malicious inputs, use the Codex CLI challenge mode. It adversarially tests your code against breaking edge cases to verify your security boundaries and input validation logic.

Does the Codex CLI support session continuity for follow-up questions?▼

Yes, the Codex CLI supports session continuity for follow-up questions in consult mode. This allows you to ask questions and receive technical guidance while maintaining context across multiple clarifications.

Related Skills

Explore More Software Engineering Skills→
a29paula29paul
1

codex

Wrap the OpenAI Codex CLI for code review, adversarial testing, and consultation.

Community
Advanced
vadimcomanescuvadimcomanescu
24

finishing-a-development-branch

Synchronize a development branch with its base and run tests and linters.

Community
Advanced
AnveioAnveio
1

task-pull-request

Automate GitHub pull request creation, reviews, feedback, and merges via gh CLI.

Community
Intermediate
FrekiManagarmFrekiManagarm

source-command-sparc-security-review

Perform static and dynamic code audits to flag security vulnerabilities.

Community
Advanced