> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentfront.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Generator

> Generate an @Agent class

Generates an `@Agent` class with LLM configuration and optional tool references.

## Usage

```bash theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}}
nx g @frontmcp/nx:agent researcher --project crm
nx g @frontmcp/nx:agent researcher --project crm --model claude-sonnet-4-5-20250514 --tools web_search,summarize
```

## Options

| Option      | Type     | Default | Description                                   |
| ----------- | -------- | ------- | --------------------------------------------- |
| `name`      | `string` | —       | **Required.** The name of the agent           |
| `project`   | `string` | —       | **Required.** The project to add the agent to |
| `model`     | `string` | `gpt-4` | The LLM model name                            |
| `tools`     | `string` | —       | Comma-separated tool names to reference       |
| `directory` | `string` | —       | Subdirectory within `src/agents/`             |

## Generated Code

```ts theme={"theme":{"light":"snazzy-light","dark":"dark-plus"}}
import { Agent, AgentContext } from '@frontmcp/sdk';

@Agent({
  name: 'researcher',
  description: 'TODO: describe what this agent does',
  llm: {
    model: 'claude-sonnet-4-5-20250514',
  },
  tools: ['web_search', 'summarize'],
  systemInstructions: 'TODO: define system instructions for this agent',
})
export default class ResearcherAgent extends AgentContext {
  async execute(input: unknown): Promise<unknown> {
    // TODO: implement agent logic
    return {};
  }
}
```