collaborate-codex

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

Updated Jan 10, 2026
One-click install
npx skills add https://github.com/vrazdalovschi/dotfiles --skill collaborate-codex
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: collaborate-codex
Source: https://github.com/vrazdalovschi/dotfiles/tree/main/claude/skills/collaborate-codex
Command: npx skills add https://github.com/vrazdalovschi/dotfiles --skill collaborate-codex

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines code analysis, refactoring, and automated editing by orchestrating the OpenAI Codex CLI, making complex coding tasks more efficient.

Core Features & Use Cases

  • Code Analysis & Refactoring: Improve code quality and structure.
  • Automated Editing: Apply changes directly to your codebase.
  • Flexible Execution: Supports various sandbox modes and output options for different needs.
  • Use Case: Debug a complex function by asking Codex to analyze it, suggest improvements, and automatically refactor the code in place.

Quick Start

Use the collaborate-codex skill to analyze the current file using the gpt-5.3-codex model with high reasoning effort in read-only mode.

Frequently Asked Questions about collaborate-codex

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

FAQPage Schema
How do I automate code refactoring using OpenAI Codex?

Automate code refactoring with OpenAI Codex by orchestrating the CLI to analyze codebases, suggest improvements, and apply structural changes directly to files in workspace-write or danger-full-access sandbox modes.

What sandbox modes does the Codex CLI support for automated code editing?

Codex CLI supports three sandbox modes for automated code editing: read-only for safe analysis, workspace-write for applying changes to the project, and danger-full-access for unrestricted system modifications.

Can I resume a previous code analysis session with OpenAI Codex?

Yes, you can resume a previous code analysis session with OpenAI Codex. The orchestration supports session resumption to continue analyzing files and solving complex coding problems across multiple interactions.

How do I configure reasoning effort and model selection for Codex code analysis?

Configure reasoning effort and model selection for Codex code analysis by specifying parameters like high reasoning effort and choosing models such as gpt-5.3-codex when initializing the CLI orchestration.

Is read-only mode sufficient for debugging complex functions with Codex?

Read-only mode is sufficient for debugging complex functions with Codex when you only need the AI to analyze code and suggest improvements without automatically writing changes to the codebase files.

What is the best way to handle file-based workflows for complex code problems in Codex?

The best way to handle file-based workflows for complex code problems in Codex is using the CLI orchestration, which enables passing files directly to the model for targeted analysis and automated in-place refactoring.