What it does

This skill documents best-practice usage of the Codex CLI for code analysis and automated editing tasks. It prescribes sandbox modes (read-only, workspace-write, danger-full-access), how to assemble commands safely (--skip-git-repo-check, piping resumes), and stderr handling to suppress thinking tokens. The guide is practical and procedural, focused on safe execution rather than modelling.

When to use it

Use this skill when the agent needs to invoke the Codex CLI to analyze or modify code, run resume sessions, or perform sandboxed operations. It's especially relevant when you must avoid specifying explicit models and when you need to suppress or surface stderr tokens intentionally.

What's included

Scripts: none bundled, the SKILL.md provides command examples and flags.
References: CLI usage patterns and resume examples are included in the body.
Instructions: Step-by-step rules for choosing sandbox mode, building codex exec commands, resuming sessions, and error-handling guidance.