aojdevstudio/agentic-utilities/ask-codex

Ask Codex Skill

Wraps the OpenAI Codex CLI (codex exec, codex resume) with explicit model + reasoning + sandbox selection so Claude Code can hand off work to Codex when its strengths fit (long-running agentic edits, GPT-5.x reasoning, network-enabled tasks).

Prerequisite: the codex CLI must be installed and authenticated on the host. Verify with codex --version before the first run.

Running a Task

1. Ask the user (via AskUserQuestion) which model to run (gpt-5.4 (Recommended — 25% faster, most capable agentic coding model), gpt-5.3-codex, or gpt-5.4-nano) AND which reasoning effort to use (high, medium, or low) in a single prompt with two questions.
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:

• -m, --model <MODEL>
• --config model_reasoning_effort="<high|medium|low>"
• --sandbox <read-only|workspace-write|danger-full-access>
• --full-auto
• -C, --cd <DIR>
• --skip-git-repo-check

1. Always use --skip-git-repo-check.
2. 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 the user specifies 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.
3. 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.
4. Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.
5. 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.