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 ! <cmd> (with /bash <cmd> 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: /acp ... always reaches the OpenClaw ACP command handler, and /status plus /unfocus stay local whenever command handling is enabled for the surface.

There are two related systems:

Commands

Standalone /... messages.

Directives

/think, /fast, /verbose, /trace, /reasoning, /elevated, /exec, /model, /queue.

Directives are stripped from the message before the model sees it.
In normal chat messages (not directive-only), they are treated as “inline hints” and do not persist session settings.
In directive-only messages (the message contains only directives), they persist to the session and reply with an acknowledgement.
Directives are only applied for authorized senders. If commands.allowFrom is set, it is the only allowlist used; otherwise authorization comes from channel allowlists/pairing plus commands.useAccessGroups. Unauthorized senders see directives treated as plain text.

Inline shortcuts

Allowlisted/authorized senders only: /help, /commands, /status, /whoami (/id).

They run immediately, are stripped before the model sees the message, and the remaining text continues through the normal flow.

Config

{
  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"`). On Discord, `false` skips slash-command registration and cleanup during startup; previously registered commands may remain visible until you remove them from the Discord app. Slack commands are managed in the Slack app and are not removed automatically. On Discord, native command specs may include `descriptionLocalizations`, which OpenClaw publishes as Discord `description_localizations` and includes in reconcile comparisons. 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 surfaces and owner-gated channel actions. 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 src/auto-reply/commands-registry.shared.ts
generated dock commands come from src/auto-reply/commands-registry.data.ts
plugin commands come from plugin 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

/new [model] archives the current session and starts a fresh one; /reset wipes the current session in place. They are not aliases.
Control UI intercepts typed /new to create and switch to a fresh dashboard session, except when session.dmScope: "main" is configured and the current parent is the agent’s main session; in that case /new resets the main session in place. Typed /reset still runs the Gateway’s in-place reset.
/reset soft [message] keeps the current transcript, drops reused CLI backend session ids, and reruns startup/system-prompt loading in-place.
/compact [instructions] compacts the session context. See Compaction.
/stop aborts the current run.
`/session idle

and/session max-age

manage thread-binding expiry. -/export-session [path]exports the current session to HTML. Alias:/export. - /export-trajectory [path]asks for exec approval, then exports a JSONL [trajectory bundle](/en/tools/trajectory) for the current session. Use it when you need the prompt, tool, and transcript timeline for one OpenClaw session. In group chats, the approval prompt and export result go to the owner privately. Alias:/trajectory`.

Model and run controls

`/think

sets the thinking level or clears the session override. Options come from the active model's provider profile; common levels areoff, minimal, low, medium, and high, with custom levels such as xhigh, adaptive, max, or binary ononly where supported. Aliases:/thinking, /t. - /verbose on|off|fulltoggles verbose output. Alias:/v. - /trace on|offtoggles plugin trace output for the current session. -/fast [status|on|off|default]shows, sets, or clears fast mode. -/reasoning [on|off|stream]toggles reasoning visibility. Alias:/reason. - /elevated [on|off|ask|full]toggles elevated mode. Alias:/elev. - /exec host=

security=

ask=

node=

shows or sets exec defaults. -/model [name|#|status]shows or sets the model. -/models [provider] [page] [limit=

|size=

|all]lists configured/auth-available providers or models for a provider; addallto browse that provider's full catalog.provider/*entries inagents.defaults.modelsmake/modeland/modelsshow discovered models only for those providers. -/queue

manages active-run queue behavior (steer, followup, collect, interrupt) plus options like debounce:0.5s cap:25 drop:summarize; /queue defaultor/queue resetclears the session override. Mid-run prompts steer by default without a queue directive. See [Command queue](/en/concepts/queue) and [Steering queue](/en/concepts/queue-steering). -/steer

injects guidance into the active run for the current session, independent of/queuemode. If steering is unavailable or the session is idle,

continues as a normal prompt. Alias:/tell`. See Steer.

Discovery and status

/help shows the short help summary.
/commands shows the generated command catalog.
/tools [compact|verbose] shows what the current agent can use right now.
/status shows execution/runtime status, Gateway and system uptime, plus provider usage/quota when available.
/diagnostics [note] is the owner-only support-report flow for Gateway bugs and Codex harness runs. It asks for explicit exec approval every time before running openclaw gateway diagnostics export --json; do not approve diagnostics with an allow-all rule. After approval, it sends a pasteable report with the local bundle path, manifest summary, privacy notes, and relevant session ids. In group chats, the approval prompt and report go to the owner privately. When the active session uses the OpenAI Codex harness, the same approval also sends relevant Codex feedback to OpenAI servers and the completed reply lists the OpenClaw session ids, Codex thread ids, and `codex resume

commands. See [Diagnostics Export](/en/gateway/diagnostics). -/crestodian

runs the Crestodian setup and repair helper from an owner DM. -/taskslists active/recent background tasks for the current session. -/context [list|detail|map|json]explains how context is assembled.mapsends a treemap image of the current session context. -/whoamishows your sender id. Alias:/id. - /usage off|tokens|full|cost` controls the per-response usage footer or prints a local cost summary.

Skills, allowlists, approvals

`/skill

[input]` runs a skill by name.

/allowlist [list|add|remove] ... manages allowlist entries. Text-only.
`/approve

resolves exec or plugin approval prompts. -/btw

asks a side question without changing future session context. Alias:/side`. See BTW.

Subagents and ACP

/subagents list|log|info inspects sub-agent runs for the current session.
/acp spawn|cancel|steer|close|sessions|status|set-mode|set|cwd|permissions|timeout|model|reset-options|doctor|install|help manages ACP sessions and runtime options.
`/focus

binds the current Discord thread or Telegram topic/conversation to a session target. -/unfocusremoves the current binding. -/agents` lists thread-bound agents for the current session.

Owner-only writes and admin

/config show|get|set|unset reads or writes openclaw.json. Owner-only. Requires commands.config: true.
/mcp show|get|set|unset reads or writes OpenClaw-managed MCP server config under mcp.servers. Owner-only. Requires commands.mcp: true.
/plugins list|inspect|show|get|install|enable|disable inspects or mutates plugin state. /plugin is an alias. Owner-only for writes. Requires commands.plugins: true.
/debug show|set|unset|reset manages runtime-only config overrides. Owner-only. Requires commands.debug: true.
/restart restarts OpenClaw when enabled. Default: enabled; set commands.restart: false to disable it.
/send on|off|inherit sets send policy. Owner-only.

Voice, TTS, channel control

/tts on|off|status|chat|latest|provider|limit|summary|audio|help controls TTS. See TTS.
/activation mention|always sets group activation mode.
`/bash

runs a host shell command. Text-only. Alias:!

. Requires commands.bash: trueplustools.elevatedallowlists. -!poll [sessionId]checks a background bash job. -!stop [sessionId]` stops a background bash job.

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:

/dock-discord (alias: /dock_discord)
/dock-mattermost (alias: /dock_mattermost)
/dock-slack (alias: /dock_slack)
/dock-telegram (alias: /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 session.identityLinks. The source sender and target peer must be in the same identity group, for example ["telegram:123", "discord:456"]. If a Telegram user with id 123 sends /dock_discord, OpenClaw stores lastChannel: "discord" and lastTo: "456" 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 /dock-telegram, /dock-slack, /dock-mattermost, 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:

/dreaming [on|off|status|help] toggles memory dreaming. See Dreaming.
/pair [qr|status|pending|approve|cleanup|notify] manages device pairing/setup flow. See Pairing.
/phone status|arm <camera|screen|writes|all> [duration]|disarm temporarily arms high-risk phone node commands.
/voice status|list [limit]|set <voiceId|name> manages Talk voice config. On Discord, the native command name is /talkvoice.
/card ... sends LINE rich card presets. See LINE.
/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:
- /bot-ping
- /bot-version
- /bot-help
- /bot-upgrade
- /bot-logs

Dynamic skill commands

User-invocable skills are also exposed as slash commands:

/skill <name> [input] always works as the generic entrypoint.
skills may also appear as direct commands like /prose when the skill/plugin registers them.
native skill-command registration is controlled by commands.nativeSkills and channels.<provider>.commands.nativeSkills.
command specs can provide descriptionLocalizations for native surfaces that support localized descriptions, including Discord.

Argument and parser notes

Commands accept an optional : between the command and args (e.g. /think: high, /send: on, /help:).
`/new

accepts a model alias,provider/model, or a provider name (fuzzy match); if no match, the text is treated as the message body. - For full provider usage breakdown, use openclaw status —usage. - /allowlist add|removerequirescommands.config=trueand honors channelconfigWrites. - In multi-account channels, config-targeted /allowlist —account

and/config set channels.

.accounts.

…also honor the target account'sconfigWrites. - /usagecontrols the per-response usage footer;/usage costprints a local cost summary from OpenClaw session logs. -/restartis enabled by default; setcommands.restart: falseto disable it. -/plugins install

accepts the same plugin specs asopenclaw plugins install: local path/archive, npm package, git:

, or clawhub:

. Managed Gateways restart automatically because plugin source modules changed. - /plugins enable|disable` updates plugin config and triggers Gateway plugin reload for new agent turns.

Channel-specific behavior

Discord-only native command: /vc join|leave|status controls voice channels (not available as text). join requires a guild and selected voice/stage channel. Requires channels.discord.voice and native commands.
Discord thread-binding commands (/focus, /unfocus, /agents, /session idle, /session max-age) require effective thread bindings to be enabled (session.threadBindings.enabled and/or channels.discord.threadBindings.enabled).
ACP command reference and runtime behavior: ACP agents.

Verbose / trace / fast / reasoning safety

/verbose is meant for debugging and extra visibility; keep it off in normal use.
/trace is narrower than /verbose: it only reveals plugin-owned trace/debug lines and keeps normal verbose tool chatter off.
/fast on|off persists a session override. Use the Sessions UI inherit option to clear it and fall back to config defaults.
/fast is provider-specific: OpenAI/OpenAI Codex map it to service_tier=priority on native Responses endpoints, while direct public Anthropic requests, including OAuth-authenticated traffic sent to api.anthropic.com, map it to service_tier=auto or standard_only. See OpenAI and Anthropic.
Tool failure summaries are still shown when relevant, but detailed failure text is only included when /verbose full is enabled.
/reasoning, /verbose, and /trace are risky in group settings: they may reveal internal reasoning, tool output, or plugin diagnostics you did not intend to expose. Prefer leaving them off, especially in group chats.

Model switching

/model persists the new session model immediately.
If the agent is idle, the next run uses it right away.
If a run is already active, OpenClaw marks a live switch as pending and only restarts into the new model at a clean retry point.
If tool activity or reply output has already started, the pending switch can stay queued until a later retry opportunity or the next user turn.
In the local TUI, /crestodian [request] returns from the normal agent TUI to Crestodian. This is separate from message-channel rescue mode and does not grant remote config authority.

Fast path and inline shortcuts

Fast path: command-only messages from allowlisted senders are handled immediately (bypass queue + model).
Group mention gating: command-only messages from allowlisted senders bypass mention requirements.
Inline shortcuts (allowlisted senders only): certain commands also work when embedded in a normal message and are stripped before the model sees the remaining text.
- Example: hey /status triggers a status reply, and the remaining text continues through the normal flow.
Currently: /help, /commands, /status, /whoami (/id).
Unauthorized command-only messages are silently ignored, and inline /... tokens are treated as plain text.

Skill commands and native arguments

Skill commands: user-invocable skills are exposed as slash commands. Names are sanitized to a-z0-9_ (max 32 chars); collisions get numeric suffixes (e.g. _2).
- `/skill

[input]runs a skill by name (useful when native command limits prevent per-skill commands). - By default, skill commands are forwarded to the model as a normal request. - Skills may optionally declarecommand-dispatch: toolto route the command directly to a tool (deterministic, no model). - Example:/prose` (OpenProse plugin) — see OpenProse.

Native command arguments: Discord uses autocomplete for dynamic options (and button menus when you omit required args). Telegram and Slack show a button menu when a command supports choices and you omit the arg. Dynamic choices are resolved against the target session model, so model-specific options such as /think levels follow that session’s /model override.

`/tools`

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

Default /tools is compact and optimized for quick scanning.
/tools verbose adds short descriptions.
Native-command surfaces that support arguments expose the same mode switch as compact|verbose.
Results are session-scoped, so changing agent, channel, thread, sender authorization, or model can change the output.
/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 /tools as a static catalog.

Usage surfaces (what shows where)

Provider usage/quota (example: “Claude 80% left”) shows up in /status for the current model provider when usage tracking is enabled. OpenClaw normalizes provider windows to % left; for MiniMax, remaining-only percent fields are inverted before display, and model_remains responses prefer the chat-model entry plus a model-tagged plan label.
Token/cache lines in /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: /status reports Execution for the effective sandbox path and Runtime for who is actually running the session: OpenClaw Pi Default, OpenAI Codex, a CLI backend, or an ACP backend.
Per-response tokens/cost is controlled by /usage off|tokens|full (appended to normal replies).
/model status is about models/auth/endpoints, not usage.

Model selection (`/model`)

/model is implemented as a directive.

Examples:

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

Notes:

/model and /model list show a compact, numbered picker (model family + available providers).
On Discord, /model and /models open an interactive picker with provider and model dropdowns plus a Submit step. The picker respects agents.defaults.models, including provider/* entries, so provider-scoped discovery can keep the picker below Discord’s 25-option component limit.
/model <#> selects from that picker (and prefers the current provider when possible).
/model status shows the detailed view, including configured provider endpoint (baseUrl) and API mode (api) when available.

Debug overrides

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

Examples:

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

Plugin trace output

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

Examples:

/trace
/trace on
/trace off

Notes:

/trace with no argument shows the current session trace state.
/trace on enables plugin trace lines for the current session.
/trace off disables them again.
Plugin trace lines can appear in /status and as a follow-up diagnostic message after the normal assistant reply.
/trace does not replace /debug; /debug still manages runtime-only config overrides.
/trace does not replace /verbose; normal verbose tool/status output still belongs to /verbose.

Config updates

/config writes to your on-disk config (openclaw.json). Owner-only. Disabled by default; enable with commands.config: true.

Examples:

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

MCP updates

/mcp writes OpenClaw-managed MCP server definitions under mcp.servers. Owner-only. Disabled by default; enable with commands.mcp: true.

Examples:

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

Plugin updates

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

Examples:

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

Surface notes

Sessions per surface

Text commands run in the normal chat session (DMs share main, groups have their own session).
Native commands use isolated sessions:
- Discord: `agent:

:discord:slash:

- Slack:agent:

:slack:slash:

(prefix configurable viachannels.slack.slashCommand.sessionPrefix) - Telegram: telegram:slash:

(targets the chat session viaCommandTargetSessionKey) - **/stop`** targets the active chat session so it can abort the current run.

Slack specifics

channels.slack.slashCommand is still supported for a single /openclaw-style command. If you enable commands.native, you must create one Slack slash command per built-in command (same names as /help). Command argument menus for Slack are delivered as ephemeral Block Kit buttons.

Slack native exception: register /agentstatus (not /status) because Slack reserves /status. Text /status still works in Slack messages.

BTW side questions

/btw is a quick side question about the current session. /side is an alias.

Unlike normal chat:

it uses the current session as background context,
in Codex harness sessions, it runs as an ephemeral Codex side thread with the current Codex permissions and native tool surface,
in non-Codex sessions, it keeps the older direct one-shot side-call behavior,
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 /btw useful when you want a temporary clarification while the main task keeps going.

Example:

/btw what are we doing right now?
/side what changed while the main run continued?

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

Slash commands

Config

Command list

Core built-in commands

Generated dock commands

Bundled plugin commands

Dynamic skill commands

/tools

Usage surfaces (what shows where)

Model selection (/model)

Debug overrides

Plugin trace output

Config updates

MCP updates

Plugin updates

Surface notes

BTW side questions

Related

`/tools`

Model selection (`/model`)