skills.rest
LGJ-Jonathan
LGJ-JonathanOFFICIAL
Explore all skills by this author →
GitHub

codex

Runs OpenAI Codex CLI for independent code review, adversarial challenge, and consult sessions.

Updated Mar 26, 2026
Search Tags:#code review#codex#multi-model#openai#adversarial testing#second opinion#diff review
One-click install
npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill codex-lgj-jonathan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: codex
Source: https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills/tree/main/gstack/codex
Command: npx skills add https://github.com/LGJ-Jonathan/Jonathan_Global_Claude_Skills --skill codex-lgj-jonathan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @openai/codex.

What problem does it solve? Getting a second opinion on your code from the same AI that wrote it creates blind spots. This Skill wraps the OpenAI Codex CLI so a different model reviews your diff, attacks your assumptions, or answers questions with session continuity, catching issues a single-model workflow misses. ## Core Features & Use Cases - Review Mode: Runs codex review against the current branch diff with a pass/fail gate based on [P1] critical findings, plus cross-model comparison when Claude's own review already ran. - Challenge Mode: Adversarially tries to break your code, probing edge cases and weak assumptions in the diff. - Consult Mode: Ask Codex anything with session continuity for follow-up questions, with adjustable reasoning effort (default medium, --xhigh override). - Use Case: Before merging a PR, run /codex review to get an independent diff review with a GATE: PASS/FAIL verdict, token cost, and persisted review log entry for the plan file's review report. ## Quick Start Ask the assistant to run /codex review on the current branch to get an independent second opinion on your diff.

Frequently Asked Questions about codex

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

FAQPage Schema
How do I get a second AI opinion on my code review?▼

Run /codex review to send your current branch diff to the OpenAI Codex CLI for an independent review. It returns a GATE: PASS or FAIL verdict based on whether any [P1] critical findings appear, along with token usage and cost.

How do I install the OpenAI Codex CLI?▼

Install it with npm install -g @openai/codex, or see the repository at github.com/openai/codex. The skill checks for the codex binary first and stops with install instructions if it is not found.

What is the difference between codex review and codex challenge?▼

Review mode runs a standard code review with a pass/fail gate on the diff. Challenge mode is adversarial: it actively tries to break your code by probing edge cases and weak assumptions rather than just listing findings.

Does codex review work with GitLab merge requests?▼

Yes. The skill detects the platform from the git remote URL and uses glab to find the merge request target branch, falling back to git-native commands like origin/HEAD detection when CLI tools are unavailable.

Can I increase the reasoning effort for a codex consult?▼

Yes. Add --xhigh anywhere in your input and the skill sets model_reasoning_effort to xhigh for all modes. Otherwise defaults are high for review and challenge, medium for consult.

Why does codex review say NOT_FOUND when I run it?▼

The codex binary is not on your PATH. Install it with npm install -g @openai/codex and verify with which codex before rerunning the skill.

Related Skills

Explore More Software Engineering Skills→
ivklgnivklgn
11

load-branch-changes

Load current branch diffs, commits, and changed files into session context.

Community
Intermediate
badbsallyybadbsallyy

prepare-pr

Rebase a GitHub pull request onto main and run automated checks.

Community
Advanced
stlwolfstlwolf
2

so-compare

Compare Codex and Claude outputs for the same prompt.

Community
Intermediate
eklyukineklyukin

codex

Obtains independent second opinions from OpenAI Codex CLI for planning, code review, and implementation review.

Community
Intermediate