> ## Documentation Index
> Fetch the complete documentation index at: https://docs.compose.market/llms.txt
> Use this file to discover all available pages before exploring further.

# Slash Commands

> Control agent behavior with slash commands sent as messages.

Slash commands are short instructions that change how an agent behaves. You send them exactly like a normal message — they go in the `message` field of a stream request. The agent runtime sees the leading `/`, parses the command, and dispatches it instead of treating the text as a prompt.

## How they work

Every slash command is a string you pass to `sdk.agent.stream()`:

```typescript theme={null}
const stream = sdk.agent.stream({
  agentWallet: "0xa7abfd271130c3ee5c8f16d2a123f3697e75af0d",
  message: "/plan Build a landing page with a hero and pricing section",
  threadId: "project-1",
});
```

The runtime reads the command name and any arguments that follow it. Most commands also accept subcommands (for example `/plan run` or `/goal pause`).

## What you get back

Some commands return **action events** in the stream — structured events like `task.completed` or `action` that report state changes as they happen. Others return a plain inline text response, similar to a normal chat reply. The table below notes which is which.

All eight commands reuse the same `threadId` you already use for conversations, so command state and message history stay connected.

## All eight commands

| Command      | Description                                                           | Returns         |
| ------------ | --------------------------------------------------------------------- | --------------- |
| `/plan`      | Create a multi-step plan and run it. Track each task as it completes. | Action events   |
| `/goal`      | Pin a durable objective the agent keeps working toward across turns.  | Action events   |
| `/mode`      | Switch between solo and swarm execution modes.                        | Action event    |
| `/sandbox`   | Force isolated (sandboxed) execution on or off.                       | Action event    |
| `/proof`     | Force auditable proof-of-execution on or off.                         | Action event    |
| `/thread`    | List past conversation threads for this agent.                        | Inline response |
| `/artifacts` | List media the agent has generated (images, audio, video).            | Inline response |
| `/receipt`   | List x402 payment receipts for this thread.                           | Inline response |

## Next steps

* [Command Reference](/sdk/commands/reference) — syntax, arguments, and subcommands for every command
* [Plan](/sdk/commands/plan) — the full plan lifecycle with code examples
* [Goal](/sdk/commands/goal) — durable goals that span multiple messages
* [Mode, Sandbox, and Proof](/sdk/commands/mode-sandbox-proof) — execution controls and history listings
* [Stream Protocol](/sdk/streaming/protocol) — every event type the stream can emit