# Plugins Overview

> Learn what plugins are, their benefits, and how they extend agent behavior.

- 网址：https://funcoding.ai/agents/cline/sdk/plugins/
- 来源：Cline 官方文档原文（英文），Apache-2.0 许可，同步于 2026-10-11
- 官方原文：https://docs.cline.bot/sdk/plugins

---
Plugins are packages of reusable agent capabilities. They let you bundle tools, lifecycle hooks, commands, and configuration into a single module that can be shared across projects or published for others to use.

## Benefits of Plugins

| Benefit | Description |
|---------|-------------|
| **Modularity** | Encapsulate related tools and hooks in a single unit. No more scattered logic. |
| **Reusability** | Share plugins across agents, projects, or teams. Publish to npm or distribute via git. |
| **Packaging** | Bundle tools, hooks, commands, message builders, and providers together. |
| **Observability** | Hook into every stage of the agent lifecycle — run start/end, model calls, tool calls, errors. |
| **Composability** | Combine multiple plugins in a single agent. Each plugin handles its own domain. |

## Extension Glossary

| Extension point | What it does |
|-----------------|--------------|
| **Tool** | Lets the model call an action (query a DB, call an API, etc.) |
| **Command** | Register slash commands to allow actions to be manually triggered |
| **Hook** | Runs lifecycle logic or policy checks at specific stages |
| **Rules** | Prompts that steer the agent and will be included in every session |
| **Events** | Register external events that will trigger agent actions |
| **Plugin** | Packages tools, hooks, commands, rules, and automation events together |

| If you need to... | Use a... |
|-------------------|----------|
| Allow the model to query a database, call an API, run a domain action | **Tool** |
| Register a user triggered action (slash command) | **Command** |
| Log runs, collect metrics, enforce policy | **Hook** handler |
| Block dangerous tool calls | **Hook** or approval policy |
| Provide consistent guidance to the model via prompts | **Rule** |
| Trigger agent action on an external event (new PR, Slack message, etc) | **Event** |
| Bundle several tools into a reusable module | **Plugin** |

## What is a Plugin?

A plugin is an `AgentPlugin` — an object that implements the SDK's extension interface. It can register tools, hook into agent lifecycle events, and provide configuration defaults.

```typescript
import { type AgentPlugin } from "@cline/sdk"

const myPlugin: AgentPlugin = {
  name: "my-plugin",
  manifest: {
    capabilities: ["tools", "hooks"],
  },
  setup(api, ctx) {
    // Register tools, commands, providers via api.registerTool(), etc.
  },
  hooks: {
    beforeTool(context) {
      // Observe or audit tool calls before they execute
    },
    afterRun(context) {
      // Log metrics, cleanup, notify after a run completes
    },
  },
}
```

Hooks are defined inside the `hooks` object, not directly on the extension. The available lifecycle hooks are `beforeRun`, `afterRun`, `beforeModel`, `afterModel`, `beforeTool`, `afterTool`, and `onEvent`.

## Next Steps

Register with `ClineCore`:

```typescript
await cline.start({
  prompt: "Analyze customer records",
  config: {
    // ...model/runtime config
    extensions: [databasePlugin],
  },
})
```

## File-Based Plugins

`ClineCore` supports plugin module paths via `pluginPaths` in session config:

```typescript
await cline.start({
  prompt: "Analyze this project",
  config: {
    // ...model/runtime config
    pluginPaths: ["/absolute/path/to/plugin.ts"],
  },
})
```

Plugin files export an `AgentPlugin`.

## Installing Plugins via CLI

Plugins can also be installed from file URLs, npm, git, or local paths using `cline plugin install`. See [Plugins](https://funcoding.ai/agents/cline/customization/plugins/) for install commands, the manifest format, and directory layout.

## Hook Stages

Hook stages include:

```txt
input
runtime_event
session_start
run_start
iteration_start
turn_start
before_agent_start
tool_call_before
tool_call_after
turn_end
stop_error
iteration_end
run_end
session_shutdown
error
```

Common stages:

| Stage | Use for |
|-------|---------|
| `before_agent_start` | Inject context or modify prompt/messages |
| `run_start` | Logging, timers, rate limits |
| `tool_call_before` | Audit or block tool calls |
| `tool_call_after` | Log results, trigger side effects |
| `run_end` | Metrics, notifications, cleanup |
| `error` | Error reporting |

## Hook Policies

Hook policies control execution behavior:

| Field | Meaning |
|-------|---------|
| `mode` | `"blocking"` or `"async"` |
| `timeoutMs` | Hook timeout |
| `retries` | Retry count |
| `retryDelayMs` | Delay between retries |
| `failureMode` | `"fail_open"` or `"fail_closed"` |
| `maxConcurrency` | Concurrent hook executions |
| `queueLimit` | Queue size before dropping |

Use `fail_closed` for policy-enforcement hooks where bypassing the hook is unsafe.

## Build a Plugin

For a step-by-step plugin tutorial, see [Writing Plugins](https://funcoding.ai/agents/cline/sdk/guides/writing-plugins/).

## SDK Examples

The [SDK repository](https://github.com/cline/cline/tree/main/sdk) includes ready-to-run plugin examples under [`examples/plugins/`](https://github.com/cline/cline/tree/main/sdk/examples/plugins), including tool registration, lifecycle metrics, notifications, custom compaction, policy guards, web search, background jobs, TypeScript LSP tools, and multi-agent teams.

See [Plugin Examples](https://funcoding.ai/agents/cline/sdk/plugin-examples/) for the full list and usage commands.