Which models can I use with this skill?

The skill supports various models including gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-max, and gpt-5.1-mini.

What is the primary use of the Codex CLI skill?

The Codex CLI skill allows Claude to run specialized Codex commands for automated code analysis, refactoring, and editing tasks using advanced OpenAI models.

Can I resume an interrupted Codex session?

Yes, the skill supports the 'resume --last' functionality, allowing you to continue a previous session while automatically inheriting the original model and sandbox settings.

What security levels does this skill provide?

You can specify sandbox modes: 'read-only' for analysis, 'workspace-write' for applying edits, or 'danger-full-access' for tasks requiring network or broad system permissions.

Codex CLI Integration

Name: Codex CLI Integration
Author: rafaelcalleja

byrafaelcalleja

•

Developer Tools

Integrates OpenAI Codex CLI into Claude Code to perform advanced code analysis, automated refactoring, and persistent execution sessions.

About

The codex-cli skill enables Claude to orchestrate complex code manipulation tasks by interfacing directly with the Codex CLI. It allows for high-precision code editing and analysis using specialized models like gpt-5.1-codex. The skill manages the entire lifecycle of a Codex task—from selecting reasoning efforts and sandbox security levels to resuming previous sessions—ensuring that developers can automate repetitive coding workflows while maintaining full control over the execution environment.

Key Features

Automated code refactoring and editing via codex exec
Granular sandbox security modes including read-only and workspace-write
Session persistence and resumption with context-aware resume commands
Configurable reasoning effort levels (low, medium, high)
Support for specialized gpt-5.1-codex model variations
1 GitHub stars

Use Cases

Performing deep code analysis using high-reasoning AI models
Resuming long-running code editing sessions without losing context
Executing large-scale automated code refactors across a workspace

About

Key Features

Automated code refactoring and editing via codex exec
Granular sandbox security modes including read-only and workspace-write
Session persistence and resumption with context-aware resume commands
Configurable reasoning effort levels (low, medium, high)
Support for specialized gpt-5.1-codex model variations
1 GitHub stars

Use Cases

Performing deep code analysis using high-reasoning AI models
Resuming long-running code editing sessions without losing context
Executing large-scale automated code refactors across a workspace