Slash commands

Commands are handled by the Gateway. Most commands must be sent as a standalone message that starts with

. The host-only bash chat command uses (with as an alias).

When a conversation or thread is bound to an ACP session, normal follow-up text routes to that ACP harness. Gateway management commands still stay local:

always reaches the OpenClaw ACP command handler, and plus stay local whenever command handling is enabled for the surface.

There are two related systems:

Commands

Directives

Inline shortcuts

Config

json5
Copy
{
  commands: {
    native: "auto",
    nativeSkills: "auto",
    text: true,
    bash: false,
    bashForegroundMs: 2000,
    config: false,
    mcp: false,
    plugins: false,
    debug: false,
    restart: true,
    ownerAllowFrom: ["discord:123456789012345678"],
    ownerDisplay: "raw",
    ownerDisplaySecret: "${OWNER_ID_HASH_SECRET}",
    allowFrom: {
      "*": ["user1"],
      discord: ["user:123"],
    },
    useAccessGroups: true,
  },
}

Enables parsing `/...` in chat messages. On surfaces without native commands (WhatsApp/WebChat/Signal/iMessage/Google Chat/Microsoft Teams), text commands still work even if you set this to `false`. Registers native commands. Auto: on for Discord/Telegram; off for Slack (until you add slash commands); ignored for providers without native support. Set `channels.discord.commands.native`, `channels.telegram.commands.native`, or `channels.slack.commands.native` to override per provider (bool or `"auto"`). `false` clears previously registered commands on Discord/Telegram at startup. Slack commands are managed in the Slack app and are not removed automatically. Registers **skill** commands natively when supported. Auto: on for Discord/Telegram; off for Slack (Slack requires creating a slash command per skill). Set `channels.discord.commands.nativeSkills`, `channels.telegram.commands.nativeSkills`, or `channels.slack.commands.nativeSkills` to override per provider (bool or `"auto"`). Enables `! ` to run host shell commands (`/bash ` is an alias; requires `tools.elevated` allowlists). Controls how long bash waits before switching to background mode (`0` backgrounds immediately). Enables `/config` (reads/writes `openclaw.json`). Enables `/mcp` (reads/writes OpenClaw-managed MCP config under `mcp.servers`). Enables `/plugins` (plugin discovery/status plus install + enable/disable controls). Enables `/debug` (runtime-only overrides). Enables `/restart` plus gateway restart tool actions. Sets the explicit owner allowlist for owner-only command/tool surfaces. This is the human operator account that can approve dangerous actions and run commands such as `/diagnostics`, `/export-trajectory`, and `/config`. It is separate from `commands.allowFrom` and from DM pairing access. Per-channel: makes owner-only commands require **owner identity** to run on that surface. When `true`, the sender must either match a resolved owner candidate (for example an entry in `commands.ownerAllowFrom` or provider-native owner metadata) or hold internal `operator.admin` scope on an internal message channel. A wildcard entry in channel `allowFrom`, or an empty/unresolved owner-candidate list, is **not** sufficient — owner-only commands fail closed on that channel. Leave this off if you want owner-only commands gated only by `ownerAllowFrom` and the standard command allowlists. Controls how owner ids appear in the system prompt. Optionally sets the HMAC secret used when `commands.ownerDisplay="hash"`. Per-provider allowlist for command authorization. When configured, it is the only authorization source for commands and directives (channel allowlists/pairing and `commands.useAccessGroups` are ignored). Use `"*"` for a global default; provider-specific keys override it. Enforces allowlists/policies for commands when `commands.allowFrom` is not set.

Command list

Current source-of-truth:

• core built-ins come from
  text

  Copy

  src/auto-reply/commands-registry.shared.ts
• generated dock commands come from
  text

  Copy

  src/auto-reply/commands-registry.data.ts
• plugin commands come from plugin
  text

  Copy

  registerCommand()
  calls
• actual availability on your gateway still depends on config flags, channel surface, and installed/enabled plugins

Core built-in commands

Sessions and runs

Model and run controls

Discovery and status

Skills, allowlists, approvals

Subagents and ACP

Owner-only writes and admin

Voice, TTS, channel control

Generated dock commands

Dock commands switch the current session's reply route to another linked channel. See Channel docking for setup, examples, and troubleshooting.

Dock commands are generated from channel plugins with native-command support. Current bundled set:

• text

  Copy

  /dock-discord
  (alias:
  text

  Copy

  /dock_discord
  )
• text

  Copy

  /dock-mattermost
  (alias:
  text

  Copy

  /dock_mattermost
  )
• text

  Copy

  /dock-slack
  (alias:
  text

  Copy

  /dock_slack
  )
• text

  Copy

  /dock-telegram
  (alias:
  text

  Copy

  /dock_telegram
  )

Use dock commands from a direct chat to switch the current session's reply route to another linked channel. The agent keeps the same session context, but future replies for that session are delivered to the selected channel peer.

Dock commands require

. The source sender and target peer must be in the same identity group, for example . If a Telegram user with id sends , OpenClaw stores and on the active session. If the sender is not linked to a Discord peer, the command replies with a setup hint instead of falling through to normal chat.

Docking changes the active session route only. It does not create channel accounts, grant access, bypass channel allowlists, or move transcript history to another session. Use

, , , or another generated dock command to switch the route again.

Bundled plugin commands

Bundled plugins can add more slash commands. Current bundled commands in this repo:

• text

  Copy

  /dreaming [on|off|status|help]
  toggles memory dreaming. See Dreaming.
• text

  Copy

  /pair [qr|status|pending|approve|cleanup|notify]
  manages device pairing/setup flow. See Pairing.
• text

  Copy

  /phone status|arm <camera|screen|writes|all> [duration]|disarm
  temporarily arms high-risk phone node commands.
• text

  Copy

  /voice status|list [limit]|set <voiceId|name>
  manages Talk voice config. On Discord, the native command name is
  text

  Copy

  /talkvoice
  .
• text

  Copy

  /card ...
  sends LINE rich card presets. See LINE.
• text

  Copy

  /codex status|models|threads|resume|compact|review|diagnostics|account|mcp|skills
  inspects and controls the bundled Codex app-server harness. See Codex harness.
• QQBot-only commands:
  • text

    Copy

    /bot-ping
  • text

    Copy

    /bot-version
  • text

    Copy

    /bot-help
  • text

    Copy

    /bot-upgrade
  • text

    Copy

    /bot-logs

Dynamic skill commands

User-invocable skills are also exposed as slash commands:

• text

  Copy

  /skill <name> [input]
  always works as the generic entrypoint.
• skills may also appear as direct commands like
  text

  Copy

  /prose
  when the skill/plugin registers them.
• native skill-command registration is controlled by
  text

  Copy

  commands.nativeSkills
  and
  text

  Copy

  channels.<provider>.commands.nativeSkills
  .

Argument and parser notes

Channel-specific behavior

Verbose / trace / fast / reasoning safety

Model switching

Fast path and inline shortcuts

Skill commands and native arguments

text

Copy

/tools

answers a runtime question, not a config question: what this agent can use right now in this conversation.

• Default
  text

  Copy

  /tools
  is compact and optimized for quick scanning.
• text

  Copy

  /tools verbose
  adds short descriptions.
• Native-command surfaces that support arguments expose the same mode switch as
  text

  Copy

  compact|verbose
  .
• Results are session-scoped, so changing agent, channel, thread, sender authorization, or model can change the output.
• text

  Copy

  /tools
  includes tools that are actually reachable at runtime, including core tools, connected plugin tools, and channel-owned tools.

For profile and override editing, use the Control UI Tools panel or config/catalog surfaces instead of treating

as a static catalog.

Usage surfaces (what shows where)

• Provider usage/quota (example: "Claude 80% left") shows up in
  text

  Copy

  /status
  for the current model provider when usage tracking is enabled. OpenClaw normalizes provider windows to
  text

  Copy

  % left
  ; for MiniMax, remaining-only percent fields are inverted before display, and
  text

  Copy

  model_remains
  responses prefer the chat-model entry plus a model-tagged plan label.
• Token/cache lines in
  text

  Copy

  /status
  can fall back to the latest transcript usage entry when the live session snapshot is sparse. Existing nonzero live values still win, and transcript fallback can also recover the active runtime model label plus a larger prompt-oriented total when stored totals are missing or smaller.
• Execution vs runtime:
  text

  Copy

  /status
  reports
  text

  Copy

  Execution
  for the effective sandbox path and
  text

  Copy

  Runtime
  for who is actually running the session:
  text

  Copy

  OpenClaw Pi Default
  ,
  text

  Copy

  OpenAI Codex
  , a CLI backend, or an ACP backend.
• Per-response tokens/cost is controlled by
  text

  Copy

  /usage off|tokens|full
  (appended to normal replies).
• text

  Copy

  /model status
  is about models/auth/endpoints, not usage.

Model selection (

text

Copy

/model

)

is implemented as a directive.

Examples:

text
Copy
/model
/model list
/model 3
/model openai/gpt-5.4
/model opus@anthropic:default
/model status

Notes:

• text

  Copy

  /model
  and
  text

  Copy

  /model list
  show a compact, numbered picker (model family + available providers).
• On Discord,
  text

  Copy

  /model
  and
  text

  Copy

  /models
  open an interactive picker with provider and model dropdowns plus a Submit step.
• text

  Copy

  /model <#>
  selects from that picker (and prefers the current provider when possible).
• text

  Copy

  /model status
  shows the detailed view, including configured provider endpoint (
  text

  Copy

  baseUrl
  ) and API mode (
  text

  Copy

  api
  ) when available.

Debug overrides

lets you set runtime-only config overrides (memory, not disk). Owner-only. Disabled by default; enable with .

Examples:

text
Copy
/debug show
/debug set messages.responsePrefix="[openclaw]"
/debug set channels.whatsapp.allowFrom=["+1555","+4477"]
/debug unset messages.responsePrefix
/debug reset

Plugin trace output

lets you toggle session-scoped plugin trace/debug lines without turning on full verbose mode.

Examples:

text
Copy
/trace
/trace on
/trace off

Notes:

• text

  Copy

  /trace
  with no argument shows the current session trace state.
• text

  Copy

  /trace on
  enables plugin trace lines for the current session.
• text

  Copy

  /trace off
  disables them again.
• Plugin trace lines can appear in
  text

  Copy

  /status
  and as a follow-up diagnostic message after the normal assistant reply.
• text

  Copy

  /trace
  does not replace
  text

  Copy

  /debug
  ;
  text

  Copy

  /debug
  still manages runtime-only config overrides.
• text

  Copy

  /trace
  does not replace
  text

  Copy

  /verbose
  ; normal verbose tool/status output still belongs to
  text

  Copy

  /verbose
  .

Config updates

writes to your on-disk config (). Owner-only. Disabled by default; enable with .

Examples:

text
Copy
/config show
/config show messages.responsePrefix
/config get messages.responsePrefix
/config set messages.responsePrefix="[openclaw]"
/config unset messages.responsePrefix

MCP updates

writes OpenClaw-managed MCP server definitions under . Owner-only. Disabled by default; enable with .

Examples:

text
Copy
/mcp show
/mcp show context7
/mcp set context7={"command":"uvx","args":["context7-mcp"]}
/mcp unset context7

Plugin updates

lets operators inspect discovered plugins and toggle enablement in config. Read-only flows can use as an alias. Disabled by default; enable with .

Examples:

text
Copy
/plugins
/plugins list
/plugin show context7
/plugins enable context7
/plugins disable context7

Surface notes

Sessions per surface

Slack specifics

BTW side questions

is a quick side question about the current session.

Unlike normal chat:

• it uses the current session as background context,
• it runs as a separate tool-less one-shot call,
• it does not change future session context,
• it is not written to transcript history,
• it is delivered as a live side result instead of a normal assistant message.

That makes

useful when you want a temporary clarification while the main task keeps going.

Example:

text
Copy
/btw what are we doing right now?

See BTW Side Questions for the full behavior and client UX details.

Related

• Creating skills
• Skills
• Skills config