COMMAND REFERENCE▌

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

Display session configuration and token usage — active model, approval policy, writable roots, and context capacity.

Summarize conversation to free context window space while keeping a high-level record of what happened.

Switch to Plan mode — the agent researches your codebase, asks clarifying questions, and produces a reviewable implementation plan before writing code.

Resume a previous chat session by folder name.

Create new rules or edit existing rules in .cursor/rules (.mdc files) for persistent project guidance.

Replace the current chat context with a summary to save tokens and free up context window space.

Analyze directory and generate a tailored GEMINI.md for persistent project memory.

Reload memory from global, project, and subdirectory GEMINI.md files without restarting.

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

Switch to Plan Mode (read-only) where Gemini produces an approved plan before making any changes.

Revert files to their pre-tool state using checkpointing. Pass a tool_call_id to restore a specific checkpoint.

Navigate backward through history; revert chat and/or code to a prior state (also Esc Esc).

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

Open the external $EDITOR for composing messages — useful for long or structured prompts. Keybind: Ctrl+x e.

Guided AGENTS.md setup for the current project.

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

Restore a previously undone message and file changes. Git-backed. Keybind: Ctrl+x r.