Slash Commands

Agents can advertise a set of slash commands that users can invoke. These commands provide quick access to specific agent capabilities and workflows. Commands are run as part of regular prompt requests where the Client includes the command text in the prompt.

Advertising commands

Initial commands

The Agent MAY include availableCommands in the session/new, session/resume, and, when supported, session/fork responses, alongside configOptions when supported. This lets the Client display commands as soon as session setup completes, without requiring an available_commands_update notification before the session/new response. For example, a session/new response can advertise a command with text input:

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "sessionId": "sess_abc123def456",
    "availableCommands": [
      {
        "name": "web",
        "description": "Search the web for information",
        "input": {
          "type": "text",
          "hint": "query to search for"
        }
      }
    ]
  }
}

AvailableCommand[]

Optional initial list of commands available in this session. Omission or [] means no initial commands are advertised. Empty lists are omitted when serializing setup responses.

null is not a valid outbound value for this field. Consistent with v2’s tolerant deserialization rules, receivers treat null or a malformed non-array value like omission and skip invalid command items within an array.

Notifications

After session setup, the Agent MAY announce commands that were not included in the response, or update the list, via the available_commands_update session notification:

{
  "jsonrpc": "2.0",
  "method": "session/update",
  "params": {
    "sessionId": "sess_abc123def456",
    "update": {
      "sessionUpdate": "available_commands_update",
      "availableCommands": [
        {
          "name": "web",
          "description": "Search the web for information",
          "input": {
            "type": "text",
            "hint": "query to search for"
          }
        },
        {
          "name": "test",
          "description": "Run tests for the current project"
        },
        {
          "name": "plan",
          "description": "Create a detailed implementation plan",
          "input": {
            "type": "text",
            "hint": "description of what to plan"
          }
        }
      ]
    }
  }
}

The notification’s availableCommands array is the complete replacement list, not a delta. An empty array clears all advertised commands.

AvailableCommand

string

required

The command name (e.g., “web”, “test”, “plan”)

string

required

Human-readable description of what the command does

AvailableCommandInput

Optional input specification for the command

AvailableCommandInput

Currently supports text input with type: "text":

string

required

A hint to display when the input hasn’t been provided yet

Command input specifications can add custom or future type values. Custom input types MUST begin with _; unknown non-underscore input types are reserved for future ACP variants. Clients that cannot render an input specification should preserve it when storing, replaying, proxying, or forwarding command metadata, and otherwise display the command without structured input.

Dynamic updates

The Agent can update the list of available commands at any time during a session by sending another available_commands_update notification. Each notification replaces the list previously advertised in a setup response or notification, including [] to clear it. This allows commands to be added based on context, removed when no longer relevant, or modified with updated descriptions.

Running commands

Commands are included as regular user messages in prompt requests:

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "session/prompt",
  "params": {
    "sessionId": "sess_abc123def456",
    "prompt": [
      {
        "type": "text",
        "text": "/web agent client protocol"
      }
    ]
  }
}

The Agent recognizes the command prefix and processes it accordingly. Commands may be accompanied by any other user message content types (images, audio, etc.) in the same prompt array. The same prompt insertion contract applies to commands: the successful response returns the inserted user message’s messageId, and the Agent reports that message through a user_message update or user_message_chunk updates with the same ID. If a command is handled locally and the runtime does not record it, the adapter inserts a live-only user message into the ACP conversation. It need not wait for a runtime insertion event or keep a permanent transcript entry. If the command is retained and replayed later, it uses the same message ID and is not executed again.

Get Started

Protocol

Libraries

Advertising commands

Initial commands

Notifications

AvailableCommand

AvailableCommandInput

Dynamic updates

Running commands

​Advertising commands

​Initial commands

​Notifications

​AvailableCommand

​AvailableCommandInput

​Dynamic updates

​Running commands

Advertising commands

Initial commands

Notifications

AvailableCommand

AvailableCommandInput

Dynamic updates

Running commands