codex

# Codex Skill Guide

## Language
All prompts passed to `codex` MUST be in English.

## Prompt Delivery
1. Write the prompt to a temporary file using the Write tool
2. Pipe the file content to codex: `cat /tmp/codex_prompt.txt | codex exec ...`

## Running a Task
1. Ask the user (via `AskUserQuestion`) which model and reasoning effort in a **single prompt with two questions**.

| Model | Characteristics |
|-------|-----------------|
| `gpt-5.2-codex` | Latest frontier agentic coding model (current default) |
| `gpt-5.1-codex-max` | Codex-optimized flagship for deep and fast reasoning |
| `gpt-5.2` | Latest frontier model with improvements across knowledge, reasoning and coding |
2. Select sandbox mode; default to `--sandbox read-only` unless edits or network access are necessary.
3. Assemble command with options (always include `--skip-git-repo-check`):
   - `-m, --model <MODEL>` / `--config model_reasoning_effort="<medium|high|xhigh>"`
   - `--sandbox <read-only|workspace-write|danger-full-access>` / `--full-auto` / `-C <DIR>`
4. Resume: `cat /tmp/codex_prompt.txt | codex exec --skip-git-repo-check resume --last 2>/dev/null`. If user requests different model/reasoning, insert flags between `exec` and `resume`.
5. Append `2>/dev/null` to suppress thinking tokens (stderr). Show stderr only for debugging.
6. Run command, summarize outcome, inform user: "Resume anytime with 'codex resume'."

### Quick Reference
| Use case | Command pattern |
| --- | --- |
| Read-only analysis | `codex exec --skip-git-repo-check -m MODEL --config ... --sandbox read-only 2>/dev/null` |
| Apply edits | `... --sandbox workspace-write --full-auto 2>/dev/null` |
| Network access | `... --sandbox danger-full-access --full-auto 2>/dev/null` |
| Resume session | `cat FILE \| codex exec --skip-git-repo-check resume --last 2>/dev/null` |
| Different dir | Add `-C <DIR>` to any command |

## Following Up
After `codex` completes, use `AskUserQuestion` to confirm next steps. Restate model/reasoning/s