Built-in Tools

The agent has access to these tools out of the box. It decides when to use them based on your messages.

Tool list

Tool	Description
`read_file`	Read the contents of a file
`write_file`	Create or overwrite a file
`edit_file`	Edit specific parts of an existing file
`list_dir`	List directory contents
`exec`	Execute a shell command
`web_search`	Search the web (requires Brave API key)
`web_fetch`	Fetch and extract content from a URL
`message`	Send a message to a chat channel
`spawn`	Start a background subagent for a complex task
`task_status`	Check progress of running background tasks

How tools work

When you send a message, the LLM decides whether it needs to use tools to answer. For example:

“What’s the weather in Tokyo?” → uses web_search or web_fetch
“Create a Python script that…” → uses write_file
“Run my tests” → uses exec
“Summarize this URL” → uses web_fetch

The agent can chain multiple tools in a single response. The maxToolIterations setting (default: 20) limits how many tool calls happen per message.

Configuration

Tool-specific settings live under tools in your config:

{
  "tools": {
    "web": {
      "search": {
        "apiKey": "YOUR_BRAVE_API_KEY",
        "maxResults": 5
      }
    },
    "exec": {
      "timeout": 60,
      "restrictToWorkspace": false
    }
  }
}

See Web Search and Shell Execution for details.

Feishu / Lark Web Search