skills.rest
dhnpmp-tech
dhnpmp-techCOMMUNITY
Explore all skills by this author →
GitHub

codex

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

Updated Mar 23, 2026
Search Tags:#code review#cli#codex#openai#adversarial testing#git diff#second opinion
One-click install
npx skills add https://github.com/dhnpmp-tech/project-agent --skill codex-dhnpmp-tech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: codex
Source: https://github.com/dhnpmp-tech/project-agent/tree/main/.claude/skills/gstack/codex
Command: npx skills add https://github.com/dhnpmp-tech/project-agent --skill codex-dhnpmp-tech

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @openai/codex.

What problem does it solve? Getting a second opinion on code changes from the same AI that wrote them creates blind spots. This Skill wraps the OpenAI Codex CLI to provide an independent, cross-model review of your branch diff, adversarial failure analysis, and general technical consultation with session continuity. ## Core Features & Use Cases - Review Mode: Runs codex review against the base branch diff with a pass/fail gate based on critical [P1] findings, plus cross-model comparison when Claude's own review already ran. - Challenge Mode: Adversarially attacks your code to find edge cases, race conditions, security holes, and failure modes, streaming Codex's reasoning traces via JSONL output. - Consult Mode: Ask Codex anything about the codebase with persistent session IDs stored in .context/codex-session-id for follow-up conversations. - Use Case: Before merging a PR, run /codex review to get an independent gate verdict, then /codex challenge security to probe for injection vectors and auth bypasses the first review missed. ## Quick Start Ask the assistant to run a codex review of the current branch diff against the base branch and report the pass/fail gate verdict.

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 the codex skill in review mode, which executes `codex review` against your branch diff with high reasoning effort. It returns a pass/fail gate based on critical [P1] findings and can compare results against Claude's own review for cross-model analysis.

How to adversarially test code for security holes with AI?▼

Use challenge mode with a focus area like security. It prompts Codex to think like an attacker, hunting for injection vectors, auth bypasses, race conditions, and silent data corruption paths in your branch diff.

What happens if the Codex CLI is not installed?▼

The skill checks for the codex binary first and stops with installation instructions if it is missing. Install it with `npm install -g @openai/codex` or see the OpenAI Codex GitHub repository.

Can I continue a previous Codex conversation?▼

Yes, consult mode stores a session ID in `.context/codex-session-id`. When a session exists, the skill asks whether to continue the prior conversation with full context or start a fresh one.

How does the codex review pass/fail gate work?▼

The gate fails if the review output contains any [P1] critical findings. Output with only [P2] findings or no findings passes. Results are persisted to a review log with finding counts and fix status.

Related Skills

Explore More Software Engineering Skills→
fwojciecfwojciec

gemini-review

Automate code reviews by querying Gemini on Git branch diffs.

Community
Advanced
badbsallyybadbsallyy

prepare-pr

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

Community
Advanced
berlysiaberlysia
9

codex-review-mcp

Automate external plan and architecture reviews via Codex MCP.

Community
Advanced
INNERJOINTINNERJOINT

ccg

Orchestrate parallel Codex and Gemini queries and synthesize outputs into a reconciled response.

Community
Intermediate