Custom tools
Create custom tools to extend opencode capabilities.
Custom tools are functions you create that the LLM can call during conversations. They work alongside opencode’s built-in tools like read
, write
, and bash
.
Tool structure
Tools are defined as .ts/.js
files in the .opencode/tool/
directory. They
can also be defined globally in ~/.config/opencode/tool/
.
The easiest way to create tools is using the tool()
helper which provides type safety and validation. Use tool.schema
(which is just Zod) to define argument types:
import { tool } from "@opencode-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}` },})
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" },}
The filename becomes the tool name. This creates a database
tool.
Multiple tools per file
You can export multiple tools from a single file. Each export becomes a separate tool with the name <filename>_<exportname>
:
import { tool } from "@opencode-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
.
Arguments
Use tool.schema
(which is just Zod) to define tool arguments with validation and descriptions:
import { tool } from "@opencode-ai/plugin"
export default tool({ description: "Perform mathematical calculations", args: { expression: tool.schema.string().describe("Mathematical expression to evaluate"), precision: tool.schema.number().optional().describe("Decimal precision"), }, async execute(args) { // Your calculation logic here return `Result: ${eval(args.expression).toFixed(args.precision || 2)}` },})
Context
Tools receive context about the current session:
import { tool } from "@opencode-ai/plugin"
export default tool({ description: "Get project information", args: {}, async execute(args, context) { // Access context information const { agent, sessionID, messageID } = context return `Agent: ${agent}, Session: ${sessionID}, Message: ${messageID}` },})