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
- 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.
- Select the sandbox mode required for the task; default to
--sandbox read-only unless edits or network access are necessary.
- 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
- Always use
--skip-git-repo-check.
- 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.
- 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.
- Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.
- 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
| Use case |
Sandbox mode |
Key flags |
| Read-only review or analysis |
read-only |
--sandbox read-only 2>/dev/null |
| Apply local edits |
workspace-write |
--sandbox workspace-write --full-auto 2>/dev/null |
| Permit network or broad access |
danger-full-access |
--sandbox danger-full-access --full-auto 2>/dev/null |
| Resume recent session |
Inherited from original |
echo "prompt" | codex exec --skip-git-repo-check resume --last 2>/dev/null (no flags allowed) |
| Run from another directory |
Match task needs |
-C <DIR> plus other flags 2>/dev/null |
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.
1---2name: ask-codex3description: OpenAI Codex CLI integration for code analysis and editing. Use when the user mentions "codex", "codex cli", "codex exec", "codex resume", "ask codex", or wants to delegate code analysis, refactoring, or automated editing to the Codex CLI. Requires the `codex` binary on PATH.4---56# Ask Codex Skill78Wraps 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).910**Prerequisite:** the `codex` CLI must be installed and authenticated on the host. Verify with `codex --version` before the first run.1112---1314## Running a Task15161. 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**.172. Select the sandbox mode required for the task; default to `--sandbox read-only` unless edits or network access are necessary.183. Assemble the command with the appropriate options:19 - `-m, --model <MODEL>`20 - `--config model_reasoning_effort="<high|medium|low>"`21 - `--sandbox <read-only|workspace-write|danger-full-access>`22 - `--full-auto`23 - `-C, --cd <DIR>`24 - `--skip-git-repo-check`254. Always use `--skip-git-repo-check`.265. 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`.276. **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.287. Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.298. **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."3031### Quick Reference3233| Use case | Sandbox mode | Key flags |34| --- | --- | --- |35| Read-only review or analysis | `read-only` | `--sandbox read-only 2>/dev/null` |36| Apply local edits | `workspace-write` | `--sandbox workspace-write --full-auto 2>/dev/null` |37| Permit network or broad access | `danger-full-access` | `--sandbox danger-full-access --full-auto 2>/dev/null` |38| Resume recent session | Inherited from original | `echo "prompt" \| codex exec --skip-git-repo-check resume --last 2>/dev/null` (no flags allowed) |39| Run from another directory | Match task needs | `-C <DIR>` plus other flags `2>/dev/null` |4041## Following Up4243- After every `codex` command, immediately use `AskUserQuestion` to confirm next steps, collect clarifications, or decide whether to resume with `codex exec resume --last`.44- 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.45- Restate the chosen model, reasoning effort, and sandbox mode when proposing follow-up actions.4647## Error Handling4849- Stop and report failures whenever `codex --version` or a `codex exec` command exits non-zero; request direction before retrying.50- 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.51- When output includes warnings or partial results, summarize them and ask how to adjust using `AskUserQuestion`.
aojdevstudio