/codex

name: codex
description: Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.

Codex Skill Guide

Always present this skill as `/architect:codex`. Never show a shorter command.

Trust boundary

`/architect:codex` is the direct, unverified lane: it runs `codex exec` against the user's checkout without an isolated worktree, frozen Candidate Artifact, or independent verification. Use it for direct CLI assistance when those controls are not required. Use `/architect:delegate` for the verified lane when changes need isolation, a frozen Candidate Artifact, independent verification, and controlled integration.

Only `/architect:delegate` produces a frozen, independently verified Candidate Artifact and drives review, decision, and guarded integration. This direct skill must never call itself verified or invoke those lifecycle tools.

Running a Task

1. For a new session (resumes inherit the prior model/effort — see step 5), ask the user (via `AskUserQuestion`) which **model** AND which **reasoning effort** to use, in a **single prompt with two questions**. When the user expresses no preference, default to `gpt-6.1-sol` at `high`.

• **Model** — default `gpt-6.1-sol`:
• *GPT-6:* `gpt-6.1-sol` (latest workhorse — **default**), `gpt-6-astra` (frontier), `gpt-6-sol` (previous generation), `gpt-6-luna` (fast & affordable)
• *Legacy (kept for compatibility):* `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.3-codex-spark`, `gpt-5.3-codex`
• **Reasoning effort** — default `high`: `low`, `medium`, `high`, `xhigh`, `max`, `ultra`.
• `max`/`ultra` require a GPT-6 model or a legacy GPT-5.6 model; `ultra` is only on `gpt-6.1-sol`, `gpt-6-astra`, `gpt-6-sol` and legacy `gpt-5.6-sol`/`gpt-5.6-terra` (luna variants cap at `max`); other legacy models cap at `xhigh`.
• `ultra` = maximum reasoning **with automatic task delegation** (slowest and most expensive — reserve for the hardest jobs).
• If the chosen effort exceeds the chosen model's maximum, fall back to that model's highest supported effort and tell the user.

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="<low|medium|high|xhigh|max|ultra>"` (max/ultra only on GPT-6 and legacy GPT-5.6 models; ultra not on luna — see step 1)
• `--sandbox <read-only|workspace-write|danger-full-access>`
• `-C, --cd <DIR>`
• `--skip-git-repo-check`
• `"your prompt here"` (as final positional argument)

4. Always use --skip-git-repo-check. 5. When continuing a previous session, prefer the positional form `codex exec --skip-git-repo-check resume --last "prompt"`. Resumed sessions inherit the prior model, reasoning effort, and sandbox. Do not add configuration flags unless the user explicitly requests an override; any such flags belong between `exec` and `resume`. 6. **IMPORTANT (stderr)**: Never discard stderr. `codex exec` sends progress, warnings, and diagnostics to stderr and its final agent message to stdout. Capture both streams separately, preserve a nonzero exit as failure, and summarize progress only after retaining actionable diagnostics. 7. **IMPORTANT (stdin)**: Prefer a positional prompt for new and resumed sessions. In a harness that may leave stdin open, close it explicitly without redirecting stderr:

• POSIX: append `</dev/null`, for example `codex exec --skip-git-repo-check --sandbox read-only "prompt" </dev/null`.
• PowerShell: prefix the native command with `$null |`, for example `$null | codex exec --skip-git-repo-check --sandbox read-only "prompt"`.
• `cmd.exe`: append `<NUL`, for example `codex exec --skip-git-repo-check --sandbox read-only "prompt" <NUL`.
• Process APIs: spawn with `stdio: ["ignore", "pipe", "pipe"]` so stdin is closed while stdout and stderr remain distinct.

8. Run the command, capture stdout and stderr separately, and summarize the outcome for the user. 9. **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 | Command | | --- | --- | | Read-only review or analysis | `codex exec --skip-git-repo-check --sandbox read-only "prompt"` | | Apply local edits | `codex exec --skip-git-repo-check --sandbox workspace-write "prompt"` | | Permit network or broad access | `codex exec --skip-git-repo-check --sandbox danger-full-access "prompt"` | | Resume recent session | `codex exec --skip-git-repo-check resume --last "prompt"` | | Run from an explicit directory | `codex exec --skip-git-repo-check -C . --sandbox read-only "prompt"` |

Execution timeouts

Codex streams intermediate progress to stderr and writes the final agent message to stdout. An empty stdout does not prove the process is hung; inspect retained stderr and the process state. If the process is killed before finishing, treat the run as failed even if it emitted partial output.

**Preferred approach:** run synchronously — eliminates timeout risk entirely and the conversation waits for the result anyway.

**If running in background**, set the execution timeout based on reasoning effort:

| Reasoning effort | Timeout | |---|---| | `low` | 150s | | `medium` | 300s | | `high` | 600s | | `xhigh` | 1200s | | `max` | 1800s | | `ultra` | 1800s |

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, pass the new prompt positionally: `codex exec --skip-git-repo-check resume --last "new prompt"`. The resumed session automatically uses the same model, reasoning effort, and sandb