codex

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

4.00x

Quality

83%

Does it follow best practices?

Impact

88%

4.00x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

The canonical home for this skill is codex in jdrhyne/agent-skills

Preview

This is a new way to view eval results. We're still working on it, so the layout may change.

Run	Type	Date	Status
baseline vs usage-spec With / without context 7 months ago Completed	With / without context	7 months ago	Completed

Eval run

019cbec0-6605-760d-96e2-cabf30af6a39

Run 7 months ago

Stats are not available yet

The run is available. Its result stats will appear here when they are ready.

Repository: softaworks/agent-toolkit
Path: skills/codex/SKILL.md
Commit: 3027f20

Evaluated: 7 months ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Automated Code Review Script Legacy Code Modernization Tool Multi-Session Security Audit Runbook

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.