Custom Tools

Create tools the LLM can call in anthracode.

Custom tools are functions you create that the LLM can call during conversations. They work alongside anthracode’s built-in tools like read, write, and bash.

Creating a tool

Tools are defined as TypeScript or JavaScript files. However, the tool definition can invoke scripts written in any language — TypeScript or JavaScript is only used for the tool definition itself.

Location

They can be defined:

Locally by placing them in the .anthracode/tools/ directory of your project.
Or globally, by placing them in ~/.config/anthracode/tools/.

Structure

The easiest way to create tools is using the tool() helper which provides type-safety and validation.

import { tool } from "@anthracode-ai/plugin"

export default tool({
  description: "Query the project database",
  args: {
    query: tool.schema.string().describe("SQL query to execute"),
  },
  async execute(args) {
    // Your database logic here
    return `Executed query: ${args.query}`
  },
})

The filename becomes the tool name. The above creates a database tool.

Multiple tools per file

You can also export multiple tools from a single file. Each export becomes a separate tool with the name <filename>_<exportname>:

import { tool } from "@anthracode-ai/plugin"

export const add = tool({
  description: "Add two numbers",
  args: {
    a: tool.schema.number().describe("First number"),
    b: tool.schema.number().describe("Second number"),
  },
  async execute(args) {
    return args.a + args.b
  },
})

export const multiply = tool({
  description: "Multiply two numbers",
  args: {
    a: tool.schema.number().describe("First number"),
    b: tool.schema.number().describe("Second number"),
  },
  async execute(args) {
    return args.a * args.b
  },
})

This creates two tools: math_add and math_multiply.

Name collisions with built-in tools

Custom tools are keyed by tool name. If a custom tool uses the same name as a built-in tool, both definitions are sent to the LLM — there is no automatic shadowing. Which implementation the model prefers depends on the model itself.

For example, this custom tool registers alongside the built-in bash tool:

import { tool } from "@anthracode-ai/plugin"

export default tool({
  description: "Restricted bash wrapper",
  args: {
    command: tool.schema.string(),
  },
  async execute(args) {
    return `blocked: ${args.command}`
  },
})

Arguments

You can use tool.schema, which is just Zod, to define argument types.

args: {
  query: tool.schema.string().describe("SQL query to execute")
}

You can also import Zod directly and return a plain object:

import { z } from "zod"

export default {
  description: "Tool description",
  args: {
    param: z.string().describe("Parameter description"),
  },
  async execute(args, context) {
    // Tool implementation
    return "result"
  },
}

Context

Tools receive context about the current session:

import { tool } from "@anthracode-ai/plugin"

export default tool({
  description: "Get project information",
  args: {},
  async execute(args, context) {
    // Access context information
    const { agent, sessionID, messageID, directory, worktree } = context
    return `Agent: ${agent}, Session: ${sessionID}, Message: ${messageID}, Directory: ${directory}, Worktree: ${worktree}`
  },
})

Use context.directory for the session working directory. Use context.worktree for the git worktree root.

Examples

Write a tool in Python

You can write your tools in any language you want. Here’s an example that adds two numbers using Python.

First, create the tool as a Python script:

import sys

a = int(sys.argv[1])
b = int(sys.argv[2])
print(a + b)

Then create the tool definition that invokes it:

import { tool } from "@anthracode-ai/plugin"
import path from "path"

export default tool({
  description: "Add two numbers using Python",
  args: {
    a: tool.schema.number().describe("First number"),
    b: tool.schema.number().describe("Second number"),
  },
  async execute(args, context) {
    const script = path.join(context.worktree, ".anthracode/tools/add.py")
    const result = await Bun.$`python3 ${script} ${args.a} ${args.b}`.text()
    return result.trim()
  },
})

Here we are using the Bun.$ utility to run the Python script.