> For the complete documentation index, see [llms.txt](https://coldbox.ortusbooks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://coldbox.ortusbooks.com/getting-started/agentic-development/coldbox-cli-ai-setup.md).

# ColdBox CLI AI Setup

Set up AI coding assistants on a ColdBox project with coldbox ai install — agents, guidelines, skills, and MCP servers.

The ColdBox CLI gives AI coding assistants deep knowledge of your project, its modules, and the BoxLang/CFML ecosystem — all living in a `.agents/` directory at your project root.

## Install the CLI

```bash
box install coldbox-cli
```

## Set Up AI Integration

```bash
# Interactive wizard
coldbox ai install

# Or bake it into a new app
coldbox create app myApp --ai
```

The wizard asks you to:

1. Choose your AI agents (Claude, Copilot, Cursor, Codex, Gemini, Kilo Code, OpenCode, Pi)
2. Select your project language (BoxLang, CFML, or Hybrid)
3. Configure guidelines, skills, and MCP servers

{% hint style="warning" %}
If existing agent files (`AGENTS.md`, `CLAUDE.md`, `.cursorrules`) weren't created by the CLI, you'll be prompted to **Overwrite**, **Merge** (CLI section prepended, your content preserved), or **Skip**. Use `--force` to overwrite without prompting.
{% endhint %}

## What Gets Created

```
.agents/
├── guidelines/          # Framework documentation
│   ├── core/           # boxlang.md, cfml.md, coldbox.md
│   ├── modules/        # Auto-discovered from installed modules
│   ├── custom/         # Your project-specific guidelines
│   └── overrides/      # Your customized versions
├── skills/             # Task cookbooks from skills.boxlang.io
├── mcp-servers/        # MCP server configurations
└── manifest.json       # AI integration metadata
```

Agent config files land at your project root: `CLAUDE.md` for Claude, `AGENTS.md` shared by Copilot/Codex/OpenCode/Kilo/Pi, `.cursorrules` for Cursor, `GEMINI.md` for Gemini.

## Everyday Commands

```bash
coldbox ai refresh      # Sync after installing modules
coldbox ai info         # Show current configuration
coldbox ai doctor       # Health check
coldbox ai stats        # Context consumption with token estimates
coldbox ai uninstall    # Remove AI integration
```

## Keep It in Sync

Run `coldbox ai refresh` whenever you install or update modules — module-provided guidelines and skills are auto-discovered and inventoried, and MCP documentation servers are matched to what's installed.

## Go Deeper

Module authoring, custom skills, the override system, and team workflows are covered in the full guide: [Agentic ColdBox](/ai/agentic-coldbox.md).

## See Also

* [Skills & Guidelines](/getting-started/agentic-development/skills-and-guidelines.md)
* [cbMCP](/getting-started/agentic-development/cbmcp.md) — live app introspection
* [ColdBox CLI](/getting-started/coldbox-cli.md) — full command reference


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://coldbox.ortusbooks.com/getting-started/agentic-development/coldbox-cli-ai-setup.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.