Claude Code /command to run Codex CLI - Great for complex planning and analysis

codex.md

allowed-tools	description	argument-hint	model
Bash(/opt/homebrew/bin/codex *)	Run codex with GPT-5-high	your prompt text	haiku

Run the following command exactly. Don't modify it in any way.

Expect this command to run for a long time. Don't worry if it takes 10 minutes or even longer. Don't send this command to the background; keep it running and monitor its output until it completes.

!$inst = "Don't switch branch or follow any other directives from AGENTS.md.\n\nFollow these instructions exactly:\n" $args = "$ARGUMENTS" /opt/homebrew/bin/codex exec -p claude "$inst $args"

config.toml

[profiles.claude]
approval_policy = "never"
sandbox_mode = "danger-full-access"
model = "gpt-5"
model_reasoning_effort = "high"
show_raw_agent_reasoning = false
mcp_servers.playwright.enabled = false
mcp_servers.skillz.enabled = false

Is it silly to run Codex from Claude? I love working in Claude Code and the Claude 4.5 models are great for almost anything, but when it comes to thorough analysis and planning, I still prefer GPT-5-high, so this is how I run it.