ToolOpenAICodex

OpenAI Codex update adds reusable prompts and settings

Original title: Codex 0.164.0

Plain language

What it is: OpenAI released a new version of Codex, version 0.164.0. This update introduces features like saving reusable prompts, setting model options directly in the command line, and previewing images in the terminal.
How it works: Users can save reusable prompts and slash commands in ten numbered slots and access them quickly using a keyboard menu. They can also set the model, speed, and permissions directly using inline commands.
Where it is available: These features are available in Codex version 0.164.0. Image previews require terminals that support Kitty or Sixel graphics.
Example: A user can save a frequently used prompt in one of the ten preset slots and open it quickly using a keyboard shortcut.

What it is: Codex version 0.164.0 has been released, introducing inline model and permission configuration, terminal image previews, and credential masking. It also adds enterprise MCP connection authentication and enables the Amazon Bedrock setup wizard by default.
How it works: Model parameters like reasoning effort and speed are configured inline using /model arguments, while permissions are set via /permissions. Credentials are automatically masked during remote Bash commands and Zsh snapshot sessions.
Where it is available: The update applies to Codex version 0.164.0. Image previews are supported on terminals with Kitty or Sixel graphics, and credential masking applies to remote Bash and Zsh sessions.
Example: Developers can set the model and reasoning effort directly in the terminal using inline /model arguments.

The headline and explanation on this page are based on OpenAI's post. The full details are in the original.

Codex 0.164.0