COMMAND REFERENCE▌

Set the model effort level: low, medium, high, xhigh, max, or ultracode. Takes effect immediately without waiting for the current response.

View hook configurations for tool events — pre- and post-tool hooks that run shell commands around Claude's actions.

Switch the AI model and save it as your default for new sessions. Adjust effort level with left/right arrows on models that support it.

Manage allow, ask, and deny rules for tool permissions. Opens a dialog to view rules by scope, add or remove rules, and review auto-mode denials.

List available skills and manage which are shown to Claude. Press t to sort by token count, Space to hide a skill.

Approve one retry of a recent auto review denial — lets Codex attempt a blocked action once under current policy.

Toggle the Fast service tier for the current model/thread, or check current state.

Choose the active model (and reasoning effort when available). Opens a picker; press s to switch for the current session only.

Set what Codex can do without asking first — switch between Auto, Read Only, or custom permission profiles mid-session.

Choose a communication style for responses — friendly, pragmatic, or none — without rewriting your instructions.

Browse and use local skills to improve task-specific behavior by loading relevant skill context.

Toggle auto-run (default) or set explicitly on/off/status. Controls whether tools run without asking for confirmation.

Sign out from Cursor.

Toggle max mode on models that support it — enables extended reasoning and capability.

Set or list available models for the current session.

Configure sandbox mode and network access settings for the current session.

Choose and optionally persist the active model. Pass --persist to save as default.

Manage folder trust settings. Trust a path so Gemini can operate there without per-action prompts.

Manage agent skills — list, enable, disable, or reload.

List available tools. Pass 'desc' for descriptions or 'nodesc' for compact list.

Toggle Vim mode for the composer. Saved to ~/.gemini/settings.json.

Add a provider and API key to connect a new AI model provider.

Toggle tool execution details in the conversation output.

List available models across all configured providers. Keybind: Ctrl+x m.

List available themes and switch the visual theme. Keybind: Ctrl+x t.

Toggle visibility of reasoning blocks in the response.