What it does

Provides operational guidance for using the Codex CLI in agent workflows. The skill documents recommended sandbox modes, flag usage, model defaults (gpt-5.2), and safe practices for running codex exec and resuming sessions. It includes step-by-step instructions for assembling commands, handling reasoning effort levels, and summarizing outcomes for users.

When to use it

Use this skill when a user requests that the agent run Codex CLI commands, perform automated code edits, or resume prior Codex sessions. It is applicable to tasks like refactoring, code review, applying local edits, or running agentic coding workflows that need explicit sandbox and safety controls.

What's included

Scripts: none bundled (has_scripts=false) — procedural CLI guidance is embedded in the SKILL.md.
References: none bundled (has_references=false).
Instructions: defaults to gpt-5.2, safe sandbox recommendations (read-only by default), append 2>/dev/null to suppress thinking tokens, and explicit error-handling and follow-up guidance.