Slash Commands
Slash commands let you control your PizzaPi session directly from the chat input. Type / to open the command picker, then select or type a command.
Using the command picker
Section titled “Using the command picker”Opening the picker
Section titled “Opening the picker”Type / at the beginning of the chat input. A popover appears listing all available commands, grouped into sections:
- Commands — built-in session and UI commands
- Extensions — commands registered by Claude Code plugins
- Prompts — prompt template shortcuts
- Skills — skill-based commands from your configuration
The list filters as you type. For example, typing /mo narrows the list to /model.
Keyboard navigation
Section titled “Keyboard navigation”| Key | Action |
|---|---|
| ↑ / ↓ | Move highlight through the list |
| Enter | Select the highlighted command |
| Escape | Close the picker |
On touch devices, tap a command to select it.
Sub-command mode
Section titled “Sub-command mode”Some commands (like /mcp) have sub-commands. When you select one of these, the picker stays open and shows the available sub-options. For example, selecting /mcp then shows status, reload, disable, and enable.
If a sub-command requires an argument (like /mcp disable), selecting it fills the input with the command prefix and positions your cursor to type the argument.
Built-in commands
Section titled “Built-in commands”Session management
Section titled “Session management”| Command | Description |
|---|---|
/new | Start a new conversation. If linked child sessions are still active, a confirmation dialog appears first. |
/resume [query] | Resume a previous session. Opens a session picker showing recent sessions with name, date, and path. Type to fuzzy-search by session name, ID, path, or first message. |
/stop | Abort the current generation. |
/restart | Restart the underlying CLI process. |
Model and reasoning
Section titled “Model and reasoning”| Command | Description |
|---|---|
/model | Open the model selector dialog. |
/cycle_model | Same as /model — opens the model selector. |
/effort | Cycle through reasoning effort levels (low → medium → high). |
/cycle_effort | Same as /effort. |
Context and planning
Section titled “Context and planning”| Command | Description |
|---|---|
/compact [instructions] | Compact the conversation context. Optionally pass custom instructions to guide summarization, e.g. /compact focus on the auth module. |
/plan | Toggle plan mode. In plan mode, the agent explores and plans without making changes (read-only). |
Session display
Section titled “Session display”| Command | Description |
|---|---|
/name <name> | Set a display name for the current session, e.g. /name auth-refactor. |
/copy | Copy the last assistant message to your clipboard. |
Introspection
Section titled “Introspection”| Command | Description |
|---|---|
/plugins | List all loaded Claude Code plugins, including their commands, hooks, skills, agents, and MCP servers. |
/skills | List all available skills from your configuration and plugins. |
/sandbox | Show the current sandbox status — mode (none/basic/full), platform, and recent violations. |
MCP server management
Section titled “MCP server management”The /mcp command manages Model Context Protocol servers. Type /mcp (with a space) to see sub-commands:
| Sub-command | Description |
|---|---|
/mcp status | Show the status of all configured MCP servers. |
/mcp reload | Reload MCP server configurations. |
/mcp disable <name> | Disable a specific MCP server by name. |
/mcp enable <name> | Re-enable a previously disabled MCP server. |
Agent sessions
Section titled “Agent sessions”| Command | Description |
|---|---|
/agents [name] | Start a new session as a named agent. Without an argument, opens a picker showing all available agent definitions. With a name, spawns directly, e.g. /agents reviewer. |
The agent picker shows each agent’s name and description. Select one to start a new session with that agent’s system prompt.
Dynamic commands
Section titled “Dynamic commands”In addition to the built-in commands above, three types of commands appear dynamically based on your configuration:
Skill commands
Section titled “Skill commands”Skills defined in your ~/.pizzapi/skills/ directory (or registered by plugins) appear in the Skills group. They are prefixed with skill: internally but shown by their short name in the picker. Running a skill command sends its content to the agent.
Extension (plugin) commands
Section titled “Extension (plugin) commands”Claude Code plugins can register custom commands. These appear in the Extensions group. Each shows the command name and description provided by the plugin.
Prompt template commands
Section titled “Prompt template commands”Prompt templates from your configuration appear in the Prompts group. Selecting one inserts the template content into the conversation.
Examples
Section titled “Examples”/new # Start a fresh session/resume auth # Find and resume a session matching "auth"/compact focus on API routes # Compact context with custom instructions/name deploy-fix # Name the current session/mcp status # Check MCP server health/mcp disable filesystem # Disable the "filesystem" MCP server/agents reviewer # Start a session as the "reviewer" agent/effort # Cycle to the next reasoning effort level/plan # Toggle read-only plan mode/copy # Copy last response to clipboard