codex

1# Codex Skill Guide
2 
3## Running a Task
41. Default to `gpt-5.2` model. Ask the user (via `AskUserQuestion`) which reasoning effort to use (`xhigh`,`high`, `medium`, or `low`). User can override model if needed (see Model Options below).
52. Select the sandbox mode required for the task; default to `--sandbox read-only` unless edits or network access are necessary.
63. Assemble the command with the appropriate options:
7   - `-m, --model <MODEL>`
8   - `--config model_reasoning_effort="<high|medium|low>"`
9   - `--sandbox <read-only|workspace-write|danger-full-access>`
10   - `--full-auto`
11   - `-C, --cd <DIR>`
12   - `--skip-git-repo-check`
133. Always use --skip-git-repo-check.
144. 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 e.g. if he species the model or the reasoning effort when requesting to resume a session. 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.
155. **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.
166. Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.
17…