Slash commands

Add an extra workspace directory to the current session. Run without a path (or with `list`) to list configured directories. When adding, choose whether to remember the directory for the project in `.kimi-code/local.toml`

Open the permission mode list with Never Ask preselected; press `Enter` to confirm. In this mode, Kimi never interrupts you; everything runs and is decided automatically

Open a side conversation in a forked sub-Agent without affecting the current main Agent turn; without a question, opens the panel first to wait for input

Answer Kimi Code product questions (CLI usage, configuration, membership, error codes) against the official docs

Compact the current conversation context to free up token usage; an optional custom instruction can hint to the model what to preserve

Copy the last assistant message to the clipboard

Create or edit a custom TUI color theme. See Themes

Configure the external editor launched by `Ctrl-G`

Exit Kimi Code CLI

Open the experimental feature panel

Export the current session as a debug ZIP archive (same behavior as `kimi export`)

Export the current session as a Markdown file

Submit feedback with optional diagnostic logs and codebase context

Fork a new session from the current one, preserving the full conversation history; you stay in the current session

Start or manage an autonomous goal

Show keyboard shortcuts and all available commands

Import Claude Code and Codex instructions, skills, and MCP settings into Kimi Code

Analyze the current codebase and generate `AGENTS.md`

Select an account or platform and log in: Kimi Code uses OAuth device-code flow; Kimi Platform uses API key login

Clear credentials for the currently selected account

List MCP servers and their connection status in the current session

Configure MCP servers and handle MCP OAuth login. See MCP

Switch the LLM model used in the current session

Start a fresh session, discarding the current context

Select a permission mode

Toggle Plan mode. Without arguments, flips the current state; explicitly passing `on`/`off` forces the setting. Simply toggling does not create an empty plan file

Open the interactive plugin manager

Open the interactive provider manager to view, add, and remove configured providers. See Platforms & Models — `/provider` and provider management

Reload the current session and apply the latest `config.toml` settings (providers, models, etc.) and `tui.toml` UI preferences, without restarting the CLI

Reload only the `tui.toml` UI preferences (theme, editor, notifications, etc.) without rebuilding the session

Pick the default model for subagents (writes `[secondary_model] default_model`; see the subagent model pool). Hidden when the subagent model pool is disabled

Browse historical sessions and switch to / restore one

Open the settings panel inside the TUI

Show the current session runtime state: version, model, working directory, permission mode, etc.

Discover and reorganize the local skill inventory into hierarchical sub-skill bundles. Includes `/sub-skill.review` (read-only proposal) and `/sub-skill.consolidate` (apply the reorganization)

Turn swarm mode on or off without sending a prompt.

Browse the background task list

Switch the terminal UI color theme

Without arguments, display the current session title; with an argument, set a new title (max 200 characters)

Undo recent prompts from the active context. Without a count, opens a selector; with a count, undoes that many prompts. Prompts before the last compaction cannot be undone. Undoing also rolls back the todo list and plan mode state produced by those prompts (code changes are not reverted)

Inspect or edit `config.toml` (model, provider, permission, hooks) and `tui.toml` (theme, editor, notifications, auto-update)

Show token usage, context consumption, and quota information

Display the Kimi Code CLI version number

Open the current session in the web UI: pick a running server to connect to, or start a new foreground server after the TUI exits. See `kimi web`

Open the permission mode list with Ask When Needed preselected; press `Enter` to confirm. In this mode, routine edits and commands run automatically; risky actions, questions, and plans still ask