Borrowing it
Nothing to install: this file belongs to cacr92/WeReply. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cacr92/WeReply/main/.claude/skills/wechat-automation/SKILL.mdgit clone --depth 1 https://github.com/cacr92/WeReplyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cacr92/wereply/wechat-automation)<a href="https://agentmods.dev/skills/cacr92/wereply/wechat-automation"><img src="https://agentmods.dev/badge/skills/cacr92/wereply/wechat-automation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cacr92/wereply/wechat-automation"><img src="https://agentmods.dev/badge/skills/cacr92/wereply/wechat-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket fail
- Snyk warn
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00111 | $0.04194 |
| Opus 5 | $0.00056 | $0.02097 |
| Sonnet 5 | $0.00022 | $0.00839 |
| Haiku 4.5 | $0.00011 | $0.00419 |
Grade A, and why
wechat-automation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 641 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat Automation Skill
Expert guidance for WeChat monitoring and automation using wxauto (Windows) and Accessibility API (macOS).
Overview
WeReply uses Platform-specific Agents to monitor WeChat conversations and control the input box:
- Windows Agent: Python 3.12 + wxauto v4
- macOS Agent: Swift + Accessibility API
- Communication: JSON protocol via stdin/stdout with Rust Orchestrator
Architecture Pattern
微信窗口
↓ (UI Automation)
Platform Agent
├→ 监听消息(定时轮询)
├→ 提取消息内容
├→ 发送到 Orchestrator (JSON via stdout)
└→ 接收命令 (JSON via stdin)
↓
控制输入框(写入建议)
Windows Agent - wxauto v4
Installation and Setup
# 安装依赖
pip install wxauto==4.0.0
# 确保微信已登录且窗口可见
Message Monitoring Pattern
import json
import time
import sys
from wxauto import WeChat
class WeChatMonitor:
def __init__(self, interval_ms: int = 500):
"""
初始化微信监听器
Args:
interval_ms: 监听间隔(毫秒),默认 500ms
"""
self.wechat = WeChat()
self.interval_ms = interval_ms
self.last_message_id = None
def start_monitoring(self):
"""开始监听微信消息"""
try:
while True:
# 获取当前聊天窗口的最新消息
messages = self.wechat.GetAllMessage()
if messages and len(messages) > 0:
latest_message = messages[-1]
# 检查是否是新消息(避免重复处理)
message_id = self._generate_message_id(latest_message)
if message_id != self.last_message_id:
self.last_message_id = message_id
self._send_message_to_orchestrator(latest_message)
# 间隔等待
time.sleep(self.interval_ms / 1000.0)
except KeyboardInterrupt:
self._send_error("监听被用户中断")
except Exception as e:
self._send_error(f"监听错误: {str(e)}")
def _generate_message_id(self, message) -> str:
"""生成消息唯一ID(用于去重)"""
# 结合时间戳、发送者、内容生成ID
content = message.get('content', '')
sender = message.get('sender', '')
timestamp = message.get('time', '')
return f"{sender}:{timestamp}:{hash(content)}"
def _send_message_to_orchestrator(self, message):
"""
发送消息到 Rust Orchestrator
格式:
{
"type": "MessageNew",
"content": "消息内容",
"sender": "发送者",
"timestamp": "2024-01-23T10:30:00"
}
"""
payload = {
"type": "MessageNew",
"content": message.get('content', ''),
"sender": message.get('sender', ''),
"timestamp": message.get('time', '')
}
# 输出到 stdout(Rust 会读取)
print(json.dumps(payload, ensure_ascii=False), flush=True)
def _send_error(self, error_message: str):
"""发送错误信息到 Orchestrator"""
payload = {
"type": "Error",
"message": error_message
}
print(json.dumps(payload, ensure_ascii=False), flush=True)
# 使用示例
if __name__ == '__main__':
monitor = WeChatMonitor(interval_ms=500)
monitor.start_monitoring()
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 641 lines · 111 tokens per session scan A dc38cc513b39
wechat-automation is a skill published in the GitHub repository cacr92/WeReply (6 stars, last pushed 7mo ago), licensed MIT. It adds 111 tokens to every session and 4,194 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…