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

# Agent-Ready Checklist

A checklist and prompt recipes for making a BoxLang project productive for AI agents.

Use this checklist to get a BoxLang project ready for an AI agent, then use the recipes to put it to work.

Want a working example instead of building this from scratch? [cbGenesis](https://cbgenesis.coldbox.org) is a ColdBox starter that already checks every box below.

## ✅ Project Checklist

* [ ] `AGENTS.md` describes the project, commands, and code standards. See [AI Setup](/getting-started/agentic-development/ai-setup.md).
* [ ] BoxLang developer skills are installed (`npx skills add ortus-boxlang/skills/boxlang-developer`) and `AGENTS.md` says when to read them. See [Skills & Guidelines](/getting-started/agentic-development/skills-and-guidelines.md).
* [ ] Web apps: `bx-playwright` is installed and `AGENTS.md` tells the agent to verify UI changes in a real browser and keep them as browser tests. See [Build an App End to End](/getting-started/agentic-development/end-to-end-with-playwright.md).
* [ ] `boxlang check` runs after every edit. See [Validate Your Code](/getting-started/agentic-development/validate-your-code.md).
* [ ] Documentation MCP servers are configured in your agent. See [AI Setup](/getting-started/agentic-development/ai-setup.md#docs-mcp-servers).
* [ ] Tests run from one command and the command is in `AGENTS.md`.
* [ ] Configuration lives in `boxlang.json` and secrets come from environment variables, not source files.
* [ ] The [BoxLang IDE](/getting-started/agentic-development/boxlang-ide.md) is installed for language intelligence and debugging.
* [ ] For running servers, `bx-mcp` is installed with a read-only security profile. See [BoxLang MCP](/getting-started/agentic-development/boxlang-mcp.md).

## 💬 Prompt Recipes

Replace the bracketed parts with your own details.

**Build a feature**

```
Read AGENTS.md and the BoxLang best practices skill. Add [feature] to this project.
Write the tests first, then the implementation. Run `boxlang check` after each edit,
then run the tests.
```

**Understand unfamiliar code**

```
Explain how [file or feature] works. Use the BoxLang docs MCP server to check
any built-in functions or components you are not sure about.
```

**Modernize CFML**

```
Read the CFML migration skill. Audit [directory] for CFML features that
need changes to run on BoxLang, list them, then propose a migration plan
before changing any code.
```

**Diagnose a slow server** (requires BoxLang+ `bx-mcp`)

```
Use the BoxLang MCP server with the read-only profile. Check cache health,
datasource pools, and slow requests, then summarize the likely causes.
```

**Add AI to your application**

```
Read the BoxLang AI docs via the MCP server. Add a chat endpoint that uses
[provider] and streams responses. Do not hard-code API keys.
```

## 🧪 Keep Agents Honest

* Ask for tests and run them. Do not accept "it should work".
* Have the agent cite the documentation page or skill it relied on.
* Review generated code the way you review a teammate's pull request.
* Use least privilege for anything an agent can reach, especially live runtime tools.


---

# 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://boxlang.ortusbooks.com/getting-started/agentic-development/agent-ready-checklist.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.