Slash commands

Commands start with / and are usually sent as a standalone message. They control the current session - switching models, adjusting reasoning depth, managing context, and more.

Commands only work for authorised senders - users on the allowlist or who have paired with the gateway. Unauthorised senders see /... tokens treated as plain text. If a command has no effect, ask your administrator to grant you access.

Commands vs directives

Commands are standalone /... messages (/reset, /status, /help).
Directives (/think, /verbose, /reasoning, /elevated, /exec, /model, /queue) can also ride in front of a normal message. A directive on its own line sticks for the session; a directive in front of a real message applies to that message only.

You can put an optional : between a command and its argument: /think: high, /send: on, /help:.

Session management

Command	Effect
`/reset`	Start a fresh conversation (new session)
`/new [model]`	Same as `/reset`, optionally on a specific model
`/compact [instructions]`	Summarise context and continue in a smaller window
`/stop`	Stop the current running response
`/restart`	Restart the agent (enabled by default)
`/export-session [path]` (alias `/export`)	Save the current conversation as a single HTML file you can open in any browser. The bot replies with the file’s location - by default it is saved in your AI’s workspace, or in the folder you name
`/send on\|off\|inherit`	Allow or pause replies in this conversation. `on` = the bot may reply, `off` = it stays silent here, `inherit` = go back to your admin’s default
`/session idle <duration\|off>`	(Discord threads) Automatically unlink a thread from its conversation after it has been quiet for a set time (e.g. `24h`, `90m`); `off` disables the timer
`/session max-age <duration\|off>`	(Discord threads) Automatically unlink a thread from its conversation once it reaches a set age, even if it is still active

Model and reasoning

Command	Effect
`/model <name>`	Switch AI model for this session (`/model` alone shows a picker)
`/models [provider]`	See which AI models are available. `/models` alone lists the providers; `/models <provider>` lists that provider’s models (on Telegram you get tappable buttons instead of a wall of text)
`/think <level>`	Set reasoning depth: `off` `\|` `minimal` `\|` `low` `\|` `medium` `\|` `high` `\|` `xhigh` `\|` `adaptive`
`/verbose on\|full\|off`	Show or hide detailed tool output
`/reasoning on\|off\|stream`	Show the model’s reasoning in a separate message (`stream` = live draft on Telegram)

/think notes:

Send /think with no argument to see the current level.
minimal thinks a little; high thinks the hardest; adaptive lets the model choose (the default on newer models).
xhigh is only supported by certain models.

Information

Command	Effect
`/status`	Gateway status, active model, provider quota
`/help`	List available commands
`/commands`	List available commands
`/whoami` (alias `/id`)	Show your sender ID
`/context [list\|detail]`	Show how the context window is being used
`/usage tokens`	Append a token count to each reply
`/usage cost`	Print a local cost summary from session logs
`/usage full`	Append a fuller usage footer
`/usage off`	Turn the usage footer off

Output and voice

Command	Effect
`/tts on`	Turn spoken replies on
`/tts off`	Turn spoken replies off
`/tts` or `/tts status`	Show the current voice settings
`/tts provider <name>`	Choose the voice engine: `edge`, `openai`, or `elevenlabs`
`/tts limit <number>`	Set how many characters of a reply may be spoken (100-4096)
`/tts summary on\|off`	For long replies: `on` has the AI shorten them before speaking, `off` simply cuts them off at the limit
`/tts audio <text>`	Turn any text you type into an audio message
`/tts help`	Show the built-in voice guide

Send /tts with no argument to see the current settings at any time.

On Discord the voice command is /voice, because Discord reserves /tts. Text /tts still works in a normal message.

Groups

Command	Effect
`/activation mention`	Bot replies only when mentioned or pinged (default)
`/activation always`	Bot considers every message (and replies only when useful)

/activation is owner-only and applies to the current group’s session.

Who the bot answers to

Command	Effect
`/allowlist`	Show who is allowed to chat with the bot in direct messages on this app
`/allowlist list group` (or `all`)	Show the group allowlist, or both lists at once
`/allowlist add <id>`	Allow a new person to chat with the bot (by their chat ID, such as a Discord user ID or a phone number, depending on the app)
`/allowlist remove <id>`	Remove someone’s access

Viewing the list always works. Adding and removing people must be enabled by your administrator, and is not available on every app - if the bot replies that the change is not supported, ask your administrator to make the change for you.

Sub-agents and other sessions

Command	Effect
`/subagents list`	Show running sub-agents
`/kill <id\|#\|all>`	Stop one or all running sub-agents
`/steer <id\|#> <message>`	Steer a running sub-agent (alias `/tell`)
`/focus <name>` (Discord)	Link a Discord thread to one sub-agent’s conversation - see Pair Discord
`/unfocus` (Discord)	Unlink the thread you are in from its conversation
`/agents`	Show which sub-agents are linked to threads, and which thread each uses
`/queue <mode>`	Control how rapid follow-up messages are handled

Tools and execution

Command	Effect
`/exec host=<target> security=<level>`	Show or set the tool execution policy (`/exec` alone shows current)
`/approve <id> allow-once\|allow-always\|deny`	Resolve a pending tool approval
`/elevated on\|off\|ask\|full`	Control elevated (host) execution, when allowed

! <command> and its alias /bash <command> run a shell command on the gateway host. They are disabled by default and require explicit administrator opt-in plus an allowlist. On most deployments they will do nothing.

Skills

Command	Effect
`/skill <name> [input]`	Run a named skill

Skills are extra capabilities your admin has installed. Available skills vary by deployment, and many show up as their own native commands too.

Inline shortcuts

A handful of commands work when embedded in a normal message and are stripped before the AI sees the rest:

/help, /commands, /status, /whoami (/id)

Example: Hey /status, and what's the weather in Sydney today?

Notes

On Discord and Telegram, most commands also appear as native commands - type / in the chat to see them.
/verbose and /reasoning can expose internal tool output and reasoning - keep them off in shared group chats.
Command-only messages from authorised senders are handled immediately (they bypass the queue and the model) and bypass group mention gating.

Getting started

Talking to your AI

Built-in tools

Help

Users

Automation

CLI command reference

Help and FAQ

Media nodes

Setup and onboarding

Voice and realtime

More agent tools

Shohin

Slash commands

Slash commands

Commands vs directives

Session management

Model and reasoning

Information

Output and voice

Groups

Who the bot answers to

Sub-agents and other sessions

Tools and execution

Skills

Inline shortcuts

Notes

​Slash commands

​Commands vs directives

​Session management

​Model and reasoning

​Information

​Output and voice

​Groups

​Who the bot answers to

​Sub-agents and other sessions

​Tools and execution

​Skills

​Inline shortcuts

​Notes

Slash commands

Commands vs directives

Session management

Model and reasoning

Information

Output and voice

Groups

Who the bot answers to

Sub-agents and other sessions

Tools and execution

Skills

Inline shortcuts

Notes