skills.rest
TarunTeja44
TarunTeja44COMMUNITY
Explore all skills by this author →
GitHub

codex

Wraps the OpenAI Codex CLI to review, challenge, and consult on code diffs.

1|Updated Feb 22, 2026
Search Tags:#diff analysis#code review#cli#codex#openai#adversarial testing#second opinion
One-click install
npx skills add https://github.com/TarunTeja44/portfolio --skill codex-tarunteja44
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: codex
Source: https://github.com/TarunTeja44/portfolio/tree/main/.agents/skills/codex
Command: npx skills add https://github.com/TarunTeja44/portfolio --skill codex-tarunteja44

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 invokes the OpenAI Codex CLI as an independent reviewer that analyzes your branch diff, adversarially probes for failure modes, or answers technical questions 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: Asks Codex anything about the codebase with saved session IDs so follow-up questions retain prior conversation context. - Use Case: Before merging a pull request, run a codex review to get an independent pass/fail verdict, then use challenge mode focused on security to probe for injection vectors and auth bypasses. ## 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.

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 a code review?▼

Run the codex review mode, which executes `codex review --base <branch>` against your current diff. It returns a pass/fail gate where any [P1] critical finding fails the gate, and compares findings with Claude's own review if one already ran.

How do I adversarially test my code for security holes?▼

Use challenge mode with an optional focus 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 an install message if missing. Install it with `npm install -g @openai/codex` or see the OpenAI codex repository for setup instructions.

Can I continue a previous Codex conversation?▼

Yes. Consult mode saves the thread session ID to .context/codex-session-id after each run. On the next invocation it asks whether to resume that session so Codex retains prior context, or start a fresh conversation.

What are the limitations of automated AI code review?▼

AI review can miss context-dependent business logic issues and may produce false positives on unfamiliar patterns. The five-minute timeout can also truncate analysis of very large diffs, so treat the gate as one signal alongside human review.

Related Skills

Explore More Software Engineering Skills→
mmnavarrmmnavarr

git-commit-push-pr

Commit, push, and open GitHub pull requests with adaptive value-first descriptions.

Community
Advanced
badbsallyybadbsallyy

prepare-pr

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

Community
Advanced
jonmummjonmumm
2

codex-review

Run OpenAI Codex on code changes and compile categorized findings.

Community
Advanced
florianbuetowflorianbuetow
12

misconfig

Detects security misconfigurations in application and infrastructure files using scanners and Grep fallback.

Community
Advanced