Codex Skill Guide
Running a Task
- Default to
gpt-5.5model. Ask the user (viaAskUserQuestion) which reasoning effort to use (xhigh,high,medium, orlow). User can override model if needed (see Model Options below). Ifgpt-5.5is unavailable in your environment, fall back togpt-5.4. - Select the sandbox mode required for the task; default to
--sandbox read-onlyunless edits or network access are necessary. - Assemble the command with the appropriate options:
- `-m
[Description truncada. Veja o README completo no GitHub.]