message-injector

Original source / Raw SKILL.md

---
name: message-injector
description: "OpenClaw plugin that prepends custom text to every user message before it reaches the agent. Use for: enforcing memory_search before replies, injecting system-level instructions, adding persistent reminders to every conversation turn. Install as a workspace extension — works on all channels including WebChat, Telegram, Slack, etc."
---

# Message Injector

A lightweight OpenClaw workspace extension that uses the `before_agent_start` hook to inject custom text into every user message via `prependContext`.

## Installation

### 1. Create the extension directory

```bash
mkdir -p ~/.openclaw/workspace/.openclaw/extensions/message-injector
```

### 2. Copy the plugin files

Copy `scripts/index.ts` and `scripts/openclaw.plugin.json` to the extension directory:

```bash
cp scripts/index.ts ~/.openclaw/workspace/.openclaw/extensions/message-injector/
cp scripts/openclaw.plugin.json ~/.openclaw/workspace/.openclaw/extensions/message-injector/
```

### 3. Add configuration

Add the following to `~/.openclaw/openclaw.json` under `plugins.entries`:

```json
"message-injector": {
  "enabled": true,
  "config": {
    "enabled": true,
    "prependText": "Your custom text here"
  }
}
```

### 4. Restart Gateway

```bash
openclaw gateway restart
```

## Configuration

| Field | Type | Default | Description |
|-------|------|---------|-------------|
| `enabled` | boolean | `true` | Enable or disable the injector |
| `prependText` | string | `""` | Text to prepend before every user message |

## Example Use Cases

**Force memory search:**
```json
"prependText": "[⚠️ 回答前必须先 memory_search 检索相关记忆，禁止凭印象回答]"
```

**Add persistent context:**
```json
"prependText": "[当前项目：my-app | 技术栈：React + Node.js | 部署环境：AWS]"
```

**Inject safety rules:**
```json
"prependText": "[RULE: Always verify file paths before deletion. Never run rm -rf without confirmation.]"
```

## How It Works

The plugin registers a `before_agent_start` hook. When triggered, it returns `{ prependContext: prependText }` which OpenClaw prepends to the user's message before the agent processes it. This is a hard injection at the Gateway level — the agent cannot skip or ignore it.

## Source Code

GitHub: https://github.com/Harukaon/openclaw-message-injector


---

## Referenced Files

> The following files are referenced in this skill and included for context.

### scripts/index.ts

```typescript
import type { OpenClawPluginApi } from "openclaw/plugin-sdk";

export default function register(api: OpenClawPluginApi) {
  const cfg = api.pluginConfig as { prependText?: string; enabled?: boolean } | undefined;
  const enabled = cfg?.enabled !== false;
  const prependText = cfg?.prependText || "";

  if (!enabled || !prependText) {
    api.logger.info("message-injector: disabled or no prependText configured.");
    return;
  }

  api.logger.info("message-injector: active.");

  api.on("before_agent_start", async (event) => {
    if (!event.prompt || event.prompt.length < 1) return;
    return { prependContext: prependText };
  });
}

```

### scripts/openclaw.plugin.json

```json
{
  "id": "message-injector",
  "name": "Message Injector",
  "description": "Prepend custom text to every user message before it reaches the agent",
  "configSchema": {
    "type": "object",
    "additionalProperties": false,
    "properties": {
      "prependText": {
        "type": "string",
        "description": "Text to prepend before every user message"
      },
      "enabled": {
        "type": "boolean",
        "description": "Enable or disable the injector"
      }
    }
  }
}

```



---

## Skill Companion Files

> Additional files collected from the skill directory layout.

### _meta.json

```json
{
  "owner": "harukaon",
  "slug": "message-injector",
  "displayName": "Message Injector",
  "latest": {
    "version": "1.0.0",
    "publishedAt": 1771837624040,
    "commit": "https://github.com/openclaw/skills/commit/b2f54fe19d65657a191562aabba9077b5cc19c08"
  },
  "history": []
}

```