> 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-unreal-engine-plugin/ai-coding-assistant/supported-coding-agents.md).

# Supported coding agents

Reference for the five coding agents AI coding setup supports, including each agent's context file, terminal support, and options.

`EConvaiMcpAgent` lists five coding agents that **Set Up AI Coding (MCP)** can configure: `Claude Code`, `Cursor`, `VS Code`, `Gemini`, and `Codex`. Use this reference to find the exact context file, terminal behavior, and agent-specific options for each one.

### Agents and context files

| Agent         | Context file                      | Location                   | Terminal configuration                            | CLI command |
| ------------- | --------------------------------- | -------------------------- | ------------------------------------------------- | ----------- |
| `Claude Code` | `CLAUDE.md`                       | Project root               | Available                                         | `claude`    |
| `Cursor`      | `.cursor/rules/convai.mdc`        | `.cursor/rules/` directory | Not available (GUI app)                           | —           |
| `VS Code`     | `.github/copilot-instructions.md` | `.github/` directory       | Not available (GUI app)                           | —           |
| `Gemini`      | `GEMINI.md`                       | Project root               | Available                                         | `gemini`    |
| `Codex`       | `AGENTS.md`                       | Project root               | Available; also has the auto-approve option below | `codex`     |

`Claude Code`, `Codex`, and `Gemini` are CLI agents — the setup dialog's terminal option is only enabled for these three, and it writes the exact `claude`, `codex`, or `gemini` command as the terminal's startup line. `Cursor` and `VS Code` are GUI apps, so the terminal option is disabled when either is selected.

### How the primer is written to the context file

When you enable **Add Convai instructions to the agent's context file**, the plugin copies the Convai primer from `Resources/AgentPrimer/ConvaiAgentPrimer.md` into the agent's context file, wrapped between two sentinel comments:

```html
<!-- >>> Convai primer (managed by Convai; edits between sentinels are overwritten) -->
...primer content...
<!-- <<< Convai primer -->
```

Re-running setup with the same agent finds the existing sentinel-delimited block and replaces only what is between the sentinels, so content you add outside the block is preserved. If the context file does not yet contain a Convai block, the write mode you choose in the dialog decides what happens:

| Write mode | Behavior                                                                                   | Default |
| ---------- | ------------------------------------------------------------------------------------------ | ------- |
| Append     | Adds the sentinel-delimited block to the end of the file, preserving any existing content. | Yes     |
| Replace    | Overwrites the file with only the sentinel-delimited block.                                | No      |

### Codex auto-approve

`Codex` has one option no other agent has: **Let Codex run unattended with no approval prompts (bypasses Codex's sandbox)**, off by default. Enabling it changes the terminal launch line from `codex` to `codex --dangerously-bypass-approvals-and-sandbox`, so Codex executes every command with no approval prompt and no sandbox. This option only appears when `Codex` is the selected agent, and it has no effect unless the terminal option is also enabled.

### Next steps

{% content-ref url="/pages/zZk2QsZWzDUbKbMVpnVN" %}
[AI coding assistant](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/ai-coding-assistant.md)
{% endcontent-ref %}

{% content-ref url="/pages/MgbGHhCLncd4SO8SWmOa" %}
[AI coding assistant quick start](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/ai-coding-assistant/quick-start.md)
{% endcontent-ref %}

{% content-ref url="/pages/vl24Qrz4dzw30TUArbNl" %}
[Convai AgentSkills](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/ai-coding-assistant/convai-agent-skills.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 following URL with the `ask` and `goal` query parameters:

```
GET https://docs.convai.com/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/ai-coding-assistant/supported-coding-agents.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 `build a script that syncs our docs to a CMS` 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.