> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/plugins-and-integrations/convai-unity-sdk/ai-coding-assistant/supported-coding-agents.md).

# Supported coding agents

The Convai Unity SDK installs a managed instruction block into a project file for each supported coding agent — Codex, Claude Code, Cursor, Gemini, and VS Code Copilot. Use this reference to find the exact file path and install behavior for each agent.

### Managed instruction files by agent

| Agent           | Managed file                         | Location                   |
| --------------- | ------------------------------------ | -------------------------- |
| Codex           | `AGENTS.md`                          | Project root               |
| Claude Code     | `CLAUDE.md`                          | Project root               |
| Cursor          | `.cursor/rules/convai-unity-sdk.mdc` | `.cursor/rules/` directory |
| Gemini          | `GEMINI.md`                          | Project root               |
| VS Code Copilot | `.github/copilot-instructions.md`    | `.github/` directory       |

The SDK resolves each path relative to the Unity project root, not the package folder.

### How the SDK installs the managed block

The install logic is identical for all five agents. When you trigger an install or update, the SDK reads the target file if it exists, removes any block already delimited by `<!-- BEGIN CONVAI UNITY SDK -->` and `<!-- END CONVAI UNITY SDK -->`, and appends a fresh block at the end of the file. If the file does not exist, the SDK creates it, including any missing parent directory such as `.cursor/rules/` or `.github/`. Content outside the sentinel markers is preserved, and the write matches the file's existing line ending (`\r\n` or `\n`).

{% hint style="info" %}
Installing, updating, or removing the managed block is a manual action — it does not run automatically. Trigger it from the Convai Editor's **AI Coding** section, or from **Convai > AI Coding Setup**.
{% endhint %}

The installed block instructs the agent to read `Packages/com.convai.convai-sdk-for-unity/AIAssistantSkills/convai-unity-sdk/SKILL.md` and its linked references for Convai-specific workflows, and to use Unity MCP tools for generic scene, GameObject, asset, script, console, and Play Mode operations, reserving [Convai's own tools](/api-docs/plugins-and-integrations/convai-unity-sdk/ai-coding-assistant/mcp-tools-reference.md) for SDK-specific configuration and diagnosis.

### Agent-specific notes

| Agent           | Note                                                                                                                                                   |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Codex           | Created at the project root the first time you install. No additional directory is required.                                                           |
| Claude Code     | Created at the project root the first time you install. No additional directory is required.                                                           |
| Cursor          | The SDK creates the `.cursor/rules/` directory if it does not exist. Any Cursor rule frontmatter already present above the managed block is preserved. |
| Gemini          | Created at the project root the first time you install. No additional directory is required.                                                           |
| VS Code Copilot | The SDK creates the `.github/` directory if it does not exist.                                                                                         |

### Next steps

{% content-ref url="/pages/oXL608mEMdrEEudHoaSJ" %}
[AI coding assistant](/api-docs/plugins-and-integrations/convai-unity-sdk/ai-coding-assistant.md)
{% endcontent-ref %}

{% content-ref url="/pages/z66YD8D1BvUpEXCOjXz9" %}
[AI coding assistant quick start](/api-docs/plugins-and-integrations/convai-unity-sdk/ai-coding-assistant/quick-start.md)
{% endcontent-ref %}

{% content-ref url="/pages/Gd4pCWmZTgamoBbmr0R2" %}
[MCP tools reference](/api-docs/plugins-and-integrations/convai-unity-sdk/ai-coding-assistant/mcp-tools-reference.md)
{% endcontent-ref %}

{% content-ref url="/pages/6KguvwDVvWMYC4R123tO" %}
[Troubleshoot AI coding assistant setup](/api-docs/plugins-and-integrations/convai-unity-sdk/ai-coding-assistant/troubleshooting.md)
{% endcontent-ref %}


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.convai.com/api-docs/plugins-and-integrations/convai-unity-sdk/ai-coding-assistant/supported-coding-agents.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.