Codex Skill Guide

Running a Task

1. Do NOT specify a model by default. The Codex CLI is configured with a ChatGPT account, and explicit model flags (-m gpt-5-codex, -m gpt-5, -m o4-mini) all fail with "not supported when using Codex with a ChatGPT account." Omitting -m lets Codex use its default model, which works. Only add -m if the user explicitly requests a specific model.
2. Select the sandbox mode required for the task; default to --sandbox read-only unless edits or network access are necessary.
3. Assemble the command with the appropriate options:
   • --sandbox <read-only|workspace-write|danger-full-access>
   • --full-auto
   • -C, --cd <DIR>
   • --skip-git-repo-check
   • -m, --model <MODEL> (only if user explicitly requests)
   • --config model_reasoning_effort="<high|medium|low>" (only if user explicitly requests)
4. Always use --skip-git-repo-check.
5. When continuing a previous session, use codex exec --skip-git-repo-check resume --last via stdin. When resuming don't use any configuration flags unless explicitly requested by the user. Resume syntax: echo "your prompt here" | codex exec --skip-git-repo-check resume --last 2>/dev/null. All flags have to be inserted between exec and resume.
6. IMPORTANT: By default, append 2>/dev/null to all codex exec commands to suppress thinking tokens (stderr). Only show stderr if the user explicitly requests to see thinking tokens or if debugging is needed.
7. Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.
8. After Codex completes, inform the user: "You can resume this Codex session at any time by saying 'codex resume' or asking me to continue with additional analysis or changes."

Quick Reference

Following Up

• After every codex command, immediately use AskUserQuestion to confirm next steps, collect clarifications, or decide whether to resume with codex exec resume --last.
• When resuming, pipe the new prompt via stdin: echo "new prompt" | codex exec resume --last 2>/dev/null. The resumed session automatically uses the same model, reasoning effort, and sandbox mode from the original session.
• Restate the chosen model, reasoning effort, and sandbox mode when proposing follow-up actions.

Error Handling

• Stop and report failures whenever codex --version or a codex exec command exits non-zero; request direction before retrying.
• Before you use high-impact flags (--full-auto, --sandbox danger-full-access, --skip-git-repo-check) ask the user for permission using AskUserQuestion unless it was already given.
• When output includes warnings or partial results, summarize them and ask how to adjust using AskUserQuestion.