Codex Setup & Configuration

Preflight check and ~/.codex/config.toml configuration helper for codex-advisor.

Mode Selection

Parse $ARGUMENTS:

Input	Action
--status or no args	Run preflight + show current config
--model MODEL	Set default model in config.toml
--effort LEVEL	Set reasoning effort in config.toml
Combined flags	Apply all settings

Preflight Check

Check Codex CLI

which codex >/dev/null 2>&1 && codex --version || echo "NOT_INSTALLED"

If NOT_INSTALLED: "Codex CLI is not installed. Install: npm install -g @openai/codex"

Check Authentication

codex --version 2>&1

If output contains "not authenticated" or "OPENAI_API_KEY": "Authentication required. Run: codex login" If version prints normally: auth is likely OK (full verification happens on first real command).

Check Official Codex Plugin

CODEX_COMPANION=$("${CLAUDE_PLUGIN_ROOT}/scripts/resolve-companion.sh")

If exit code non-zero (plugin not found), guide the user through the full installation process:

1. Tell the user to run these commands in order (they must type these themselves since they are interactive CLI commands):
   • /plugin marketplace add openai/codex-plugin-cc — adds the Official Codex marketplace
   • /plugin install codex@openai-codex — installs the plugin from that marketplace
   • /reload-plugins — activates the newly installed plugin
2. After the user completes the steps, re-run the companion check to verify.

Do NOT just print the steps and move on. Wait for the user to complete them.

If found, run setup check:

node "$CODEX_COMPANION" setup --json

Include the setup output in the status report.

Configuration Management

Read current config:

cat ~/.codex/config.toml 2>/dev/null || echo "NO_CONFIG"

Set Model (--model)

Valid models: gpt-5.4, gpt-5.4-mini, gpt-5.3-codex-spark, or any model string.

1. Ensure directory exists: mkdir -p ~/.codex
2. If ~/.codex/config.toml doesn't exist, create it with model = "NEW_MODEL"
3. If it exists, use the Edit tool to replace the model = "..." line. If no model line exists, append it.

Set Reasoning Effort (--effort)

Valid levels: none, minimal, low, medium, high, xhigh.

1. If ~/.codex/config.toml doesn't exist, create with model_reasoning_effort = "NEW_EFFORT"
2. If it exists, use the Edit tool to replace the model_reasoning_effort = "..." line. If no such line exists, append it.

Status Report

## Codex Setup Status

| Item | Status |
|------|--------|
| Codex CLI | version or NOT_INSTALLED |
| Authentication | OK or FAILED |
| Official Plugin | OK or NOT_INSTALLED (required) |

## Current Configuration (~/.codex/config.toml)

| Setting | Value |
|---------|-------|
| model | <current or "default (not set)"> |
| model_reasoning_effort | <current or "default (not set)"> |
| web_search | <current or "default (not set)"> |

These defaults apply to ALL Codex commands — both Official plugin and direct CLI.
To change: `/codex-setup --model gpt-5.4-mini --effort high`

Gotchas

• config.toml applies globally. Changes affect all Codex commands system-wide, not just codex-advisor.
• Official /codex:review ignores --model flag. The only way to change the review model is via config.toml — that's why this skill exists.
• Don't create config.toml if user only asked for status. Only write when explicitly setting values.