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

# Slash Command Reference

> Complete reference for UltraClaw slash commands and directives. Control your AI assistant with /status, /model, /think, /tts, and more.

# Slash Command Reference

Slash commands and directives give you direct control over your AI agent's behavior. Send them as a message on iMessage, Telegram, WhatsApp, Discord, or WebChat — they work identically across all channels.

## Commands vs. Directives

There are two related systems:

| Type          | What it does                                                                             | Example                                           |
| ------------- | ---------------------------------------------------------------------------------------- | ------------------------------------------------- |
| **Command**   | A standalone message handled entirely by the gateway — never reaches the AI              | `/status` sent alone                              |
| **Directive** | A modifier that persists to your session and is stripped before the AI sees your message | `/model opus` sent alone, or `:model opus` inline |

Directives can be sent as standalone messages (they persist to the session) or **inline** in a normal message (they apply to that message only and don't persist).

```
# Standalone directive — persists to session:
/think high

# Inline directive — applies to this message only:
:think high :model opus
What are the tax implications of converting my LLC to an S-Corp?
```

***

## Session Control

<AccordionGroup>
  <Accordion title="/new [model] — Start a fresh session">
    Start a new conversation session. Your memory and workspace files carry over — only the conversation context resets. Optionally specify a model to switch to.

    ```
    /new
    /new opus
    /new gpt
    /new gemini
    ```

    Alias: `/reset` works the same as `/new`.
  </Accordion>

  <Accordion title="/compact [instructions] — Summarize context">
    Summarize the current conversation context into a condensed form, freeing up tokens. Optionally pass instructions to guide what the summary should focus on.

    ```
    /compact
    /compact focus on the marketing plan discussion
    ```

    Useful when you're deep into a long conversation and want to keep going without starting over.
  </Accordion>

  <Accordion title="/stop — Abort current action">
    Immediately abort whatever your agent is currently doing and clear any queued messages.

    ```
    /stop
    ```
  </Accordion>

  <Accordion title="/queue — Manage the message queue">
    View or configure how your agent handles queued messages. Supports `debounce`, `cap`, and `drop` options.

    ```
    /queue
    /queue debounce:2s
    /queue cap:25 drop:summarize
    ```

    Send `/queue` alone to see your current queue settings.
  </Accordion>
</AccordionGroup>

***

## Model & Thinking

<AccordionGroup>
  <Accordion title="/model — Switch AI model (directive)">
    Switch to a different AI model. This is a **directive** — it persists to your session when sent alone, or applies to a single message when used inline as `:model`.

    ```
    /model
    /model list
    /model opus
    /model gpt
    /model gemini
    /model openai/gpt-4o
    ```

    Alias: `/models`. Send `/model` or `/model list` to see a numbered model picker. Use `/model <number>` to select from the list.
  </Accordion>

  <Accordion title="/think [level] — Set reasoning depth (directive)">
    Control how much reasoning your agent does before responding. Higher levels produce more thoughtful answers but use more tokens.

    | Level      | Description                                     |
    | ---------- | ----------------------------------------------- |
    | `off`      | No extended reasoning — fastest responses       |
    | `minimal`  | Light reasoning for simple tasks                |
    | `low`      | Brief analysis before responding                |
    | `medium`   | Balanced reasoning (default for most models)    |
    | `high`     | Deep analysis and step-by-step thinking         |
    | `xhigh`    | Maximum reasoning depth for complex problems    |
    | `adaptive` | Agent decides the appropriate level per message |

    ```
    /think high
    /think adaptive
    /think off
    ```

    Aliases: `/thinking`, `/t`. Also works inline: `:think high`.
  </Accordion>

  <Accordion title="/reasoning — Toggle reasoning output (directive)">
    Control whether your agent sends its reasoning as a separate message before the final response. Useful for seeing how your agent arrived at an answer.

    ```
    /reasoning on
    /reasoning off
    /reasoning stream
    ```

    `stream` mode shows reasoning as a Telegram draft in real time (Telegram only). Alias: `/reason`.

    <Warning>
      Use `/reasoning` for personal debugging only — avoid enabling it in group chats where internal reasoning output could be visible to others unintentionally.
    </Warning>
  </Accordion>
</AccordionGroup>

***

## Output & Display

<AccordionGroup>
  <Accordion title="/tts — Text-to-speech control">
    Control voice message output. When enabled, your agent sends voice messages in addition to (or instead of) text.

    | Option     | Description                                |
    | ---------- | ------------------------------------------ |
    | `off`      | No voice messages                          |
    | `always`   | Voice on every response                    |
    | `inbound`  | Voice only when you send a voice message   |
    | `tagged`   | Voice only when response is tagged for TTS |
    | `status`   | Show current TTS settings                  |
    | `provider` | Show or set the TTS provider               |
    | `limit`    | Set a character limit for TTS responses    |
    | `summary`  | Voice summary only (not full response)     |
    | `audio`    | Audio-only mode (no text)                  |

    ```
    /tts always
    /tts off
    /tts inbound
    /tts status
    ```
  </Accordion>

  <Accordion title="/verbose — Verbose output (directive)">
    Enable detailed output including tool call results and failure details. Intended for debugging and extra visibility.

    ```
    /verbose on
    /verbose full
    /verbose off
    ```

    `full` includes all tool output. `on` shows summaries. Alias: `/v`. Also works inline: `:verbose`.

    <Warning>
      Keep `/verbose` off in normal use and in group chats — it can expose internal tool output you may not intend to share.
    </Warning>
  </Accordion>

  <Accordion title="/usage — Per-response usage footer">
    Control whether your agent appends a token/cost summary to each response.

    ```
    /usage tokens
    /usage full
    /usage cost
    /usage off
    ```

    `tokens` shows token counts. `full` adds cost. `cost` prints a local cost summary from session logs. `off` disables the footer.
  </Accordion>

  <Accordion title="/send — Override message delivery">
    Control whether your agent sends its response after processing.

    ```
    /send off
    /send on
    /send inherit
    ```

    When `off`, your agent processes your request but doesn't deliver the response — useful for testing. Also works inline: `:send off`.
  </Accordion>
</AccordionGroup>

***

## Information

<AccordionGroup>
  <Accordion title="/status — Current agent status">
    Check your agent's current state — which model is active, context window usage, queued messages, and runtime mode. Also shows provider quota when available.

    ```
    /status
    ```
  </Accordion>

  <Accordion title="/context — Token usage details">
    View detailed token usage for your current conversation.

    ```
    /context
    /context list
    /context detail
    /context json
    ```

    | Mode        | Description                                            |
    | ----------- | ------------------------------------------------------ |
    | *(default)* | Summary of token usage                                 |
    | `list`      | Itemized breakdown by message                          |
    | `detail`    | Per-file, per-tool, per-skill, and system prompt sizes |
    | `json`      | Machine-readable JSON output                           |
  </Accordion>

  <Accordion title="/whoami — Your sender identity">
    Check your sender identity as your agent sees it. Useful when you have multiple channels connected.

    ```
    /whoami
    ```

    Alias: `/id`.
  </Accordion>

  <Accordion title="/help — Quick command reference">
    Display a quick reference of the most common commands, grouped by category.

    ```
    /help
    ```
  </Accordion>

  <Accordion title="/commands — Full command list">
    List all available commands for your agent, including any installed skill commands.

    ```
    /commands
    ```
  </Accordion>
</AccordionGroup>

***

## Skills & Export

<AccordionGroup>
  <Accordion title="/skill — Run a skill by name">
    Invoke a specific skill directly by name. Useful when native command limits prevent per-skill commands from being registered.

    ```
    /skill weekly-report
    /skill summarize-emails
    ```

    See [Skills](/assistant/skills) for more on creating and managing skills.
  </Accordion>

  <Accordion title="/export-session — Export conversation to HTML">
    Export your current session to a self-contained HTML file with the full conversation and system prompt.

    ```
    /export-session
    /export-session /path/to/output.html
    ```

    Alias: `/export`. Useful for archiving conversations or sharing session context.
  </Accordion>
</AccordionGroup>

***

## Inline Directives

Directives work **inline** in a normal message to modify how your agent handles that specific message only. They don't persist to the session when used inline.

| Directive     | Effect                                     |
| ------------- | ------------------------------------------ |
| `:think high` | Apply high reasoning to this message only  |
| `:model opus` | Use a specific model for this message only |
| `:send off`   | Process but don't deliver the response     |
| `:verbose`    | Return a more detailed response than usual |

**Example:**

```
:think high :model opus
What are the tax implications of converting my LLC to an S-Corp?
```

Directives are stripped from your message before your agent reads it — they only affect processing behavior.

***

## Stop Phrases

Need your agent to stop immediately? Just say "stop" in any form:

* "stop"
* "please stop"
* "STOP!"
* "cancel"

Stop phrases are recognized in **10+ languages** — your agent understands urgency regardless of which language you use.

<Warning>
  Stop phrases abort the current action and clear the queue, similar to `/stop`. If your agent is mid-task (like drafting a long email), you'll need to ask it to start again.
</Warning>

***

## Quick Reference

| Command / Directive          | Type      | What It Does                        |
| ---------------------------- | --------- | ----------------------------------- |
| `/new [model]`               | Command   | Fresh session (alias: `/reset`)     |
| `/compact [instructions]`    | Command   | Summarize context, free tokens      |
| `/stop`                      | Command   | Abort current action + clear queue  |
| `/queue`                     | Directive | View or configure message queue     |
| `/model [name]`              | Directive | Switch AI model (alias: `/models`)  |
| `/think [level]`             | Directive | Set reasoning depth                 |
| `/reasoning on\|off\|stream` | Directive | Toggle reasoning output             |
| `/tts [option]`              | Command   | Text-to-speech control              |
| `/verbose on\|full\|off`     | Directive | Verbose output mode                 |
| `/usage [option]`            | Command   | Per-response usage footer           |
| `/send on\|off`              | Directive | Override message delivery           |
| `/status`                    | Command   | Model, context, queue, runtime mode |
| `/context [mode]`            | Command   | Token usage details                 |
| `/whoami`                    | Command   | Sender identity (alias: `/id`)      |
| `/help`                      | Command   | Grouped command reference           |
| `/commands`                  | Command   | Full command list                   |
| `/skill [input]`             | Command   | Run a skill by name                 |
| `/export-session [path]`     | Command   | Export session to HTML              |

<Info>
  All commands and directives work identically on **iMessage, Telegram, WhatsApp, Discord, and WebChat**. There are no channel-specific commands (except `/tts stream` which is Telegram-only).
</Info>