> For the complete documentation index, see [llms.txt](https://docs.chaingpt.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.chaingpt.org/dev-docs-b2b-saas-api-and-sdk/chaingpt-claude-skill-and-plugin/resources/plugin-architecture.md).

# Plugin Architecture

## Plugin Architecture

### Overview

The ChainGPT Claude Code plugin is organized in three layers: the skill layer (knowledge and templates), the MCP server (tool execution), and the ChainGPT APIs (backend services).

```
.claude-plugin/
plugin.json          # Plugin manifest (name, version, capabilities)
.mcp.json              # MCP server configuration
# Uses ${CLAUDE_PLUGIN_ROOT} for portable paths
skills/                # Auto-discovered by Claude Code
SKILL.md             # Main entry point
reference/             # 16 product and API reference documents
templates/             # Code templates for common integrations
patterns/              # Composition patterns for multi-product workflows
mcp-server/            # MCP server source (12 tools)
mock-server/           # Local testing server (localhost:3001)
```

**Total: 76 files** across all directories.

#### Key Configuration Files

**plugin.json** is the manifest that declares the plugin's identity, version, and capabilities. Claude Code reads this to register the plugin.

**.mcp.json** configures the MCP server connection. It uses the `${CLAUDE_PLUGIN_ROOT}` variable so paths resolve correctly regardless of where the plugin is installed.

**skills/** contains SKILL.md and is auto-discovered by Claude Code. This is the primary interface between the user's intent and the plugin's capabilities.


---

# 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.chaingpt.org/dev-docs-b2b-saas-api-and-sdk/chaingpt-claude-skill-and-plugin/resources/plugin-architecture.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.