codex

Orchestrate OpenAI Codex CLI operations for code analysis, refactoring, and automated editing.

Updated Dec 13, 2024
One-click install
npx skills add https://github.com/neo-picasso-2112/dotfiles --skill codex-neo-picasso-2112
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codex
Source: https://github.com/neo-picasso-2112/dotfiles/tree/main/.claude/skills/skill-codex
Command: npx skills add https://github.com/neo-picasso-2112/dotfiles --skill codex-neo-picasso-2112

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill coordinates Codex CLI workflows (codex exec, codex resume) to simplify model selection, reasoning levels, sandbox choices, and session management for code analysis, refactoring, and automated editing.

Core Features & Use Cases

  • Guided orchestration of codex exec commands with model and reasoning settings.
  • Automatic assembly of commands with required flags (-m/--model, --config, --sandbox, --full-auto, -C, --skip-git-repo-check) for repeatable workflows.
  • Support for resuming previous Codex sessions using the resume syntax, enabling iterative analysis and edits.

Quick Start

Tell me you want to run Codex with a specific model and reasoning level, and I will execute codex exec with the correct flags and defaults.

Frequently Asked Questions about codex

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

FAQPage Schema
How do I automate code refactoring and analysis using the OpenAI Codex CLI?

You can automate code refactoring by orchestrating Codex CLI operations using guided commands that automatically assemble required flags for model selection, reasoning levels, and sandbox execution. This ensures repeatable workflows for code analysis and automated editing.

Can I resume a previous Codex session to apply iterative improvements to my repository?

Yes, you can resume previous Codex sessions using the resume syntax to apply iterative improvements. This enables continuous code analysis and automated edits across multiple interactions without losing prior context.

What's the best way to manage model selection and reasoning effort for automated code editing?

The best way to manage model selection is through guided orchestration of codex exec commands. It automatically assembles required flags like -m/--model and reasoning settings, ensuring predictable and auditable commands for automated editing.

Do I need to configure sandbox mode and skip-git-repo-check when running codex exec commands?

You do not need to manually configure these settings. The orchestration enforces safe defaults by automatically applying the --skip-git-repo-check flag and sandbox mode, ensuring predictable and auditable command execution.

Why should I use orchestrated commands instead of manually running Codex CLI for repository analysis?

Using orchestrated commands ensures safe defaults and explicit prompts to choose options, creating predictable and auditable commands. Manual execution risks misconfigured flags, whereas guided orchestration automatically assembles required settings for reliable repository analysis.