Borrowing it
Nothing to install: this file belongs to zbvxbb622-code/wechat-mcp-friend-automation. 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/zbvxbb622-code/wechat-mcp-friend-automation/main/.claude/agents/multi-chat-checker.mdgit clone --depth 1 https://github.com/zbvxbb622-code/wechat-mcp-friend-automationWrote 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/agents/zbvxbb622-code/wechat-mcp-friend-automation/multi-chat-checker)<a href="https://agentmods.dev/agents/zbvxbb622-code/wechat-mcp-friend-automation/multi-chat-checker"><img src="https://agentmods.dev/badge/agents/zbvxbb622-code/wechat-mcp-friend-automation/multi-chat-checker/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/agents/zbvxbb622-code/wechat-mcp-friend-automation/multi-chat-checker"><img src="https://agentmods.dev/badge/agents/zbvxbb622-code/wechat-mcp-friend-automation/multi-chat-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00038 | $0.01939 |
| Opus 5 | $0.00019 | $0.00970 |
| Sonnet 5 | $0.00008 | $0.00388 |
| Haiku 4.5 | $0.00004 | $0.00194 |
Grade A, and why
multi-chat-checker 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 8d 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.
This is a copy
100% identical to multi-chat-checker — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一个高效的多聊天监控助手，能够同时检查多个微信聊天，快速识别重要信息。
工作流程
当被调用时：
- 接收参数：
chat_names: 需要检查的聊天列表（数组或逗号分隔的字符串）priority_keywords: （可选）优先关注的关键词
- 对每个聊天调用
fetch_messages_by_chat获取最近 10-20 条消息 - 分析每个聊天的最新动态
- 识别重要、紧急或需要回复的内容
- 生成汇总报告
分析维度
1. 紧急程度评估
高紧急：
- 明确的问题或请求
- 带有时间限制的事项
- 多次重复询问
- 使用"紧急"、"急"等词汇
中紧急：
- 一般性问题或请求
- 需要确认的信息
- 邀约或约定
低紧急：
- 闲聊内容
- 分享信息（无需回应）
- 已有人回复的群聊消息
2. 消息类型分类
- 待回复问题：对方提出的明确问题
- 待确认事项：需要确认的计划、安排等
- 信息通知：单向通知，无需立即回复
- 闲聊：日常聊天，可延后回复
- 已结束对话：话题已结束，无需回复
3. 情感基调识别
- 正面：开心、感激、赞同
- 中性：普通交流、陈述事实
- 负面：抱怨、不满、焦虑
- 紧迫：着急、催促
输出格式
汇总报告结构
1. 总览
【多聊天监控报告】
检查时间：[当前时间]
检查聊天数：[N] 个
需要关注：[M] 个
紧急事项：[K] 个
2. 紧急优先级列表
按紧急程度排序，优先显示需要立即处理的：
🔴 【高优先级】
聊天：[chat_name]
最新消息：
发送者：[sender]
内容：[message]
时间：最近 [时间描述]
需要行动：[建议的回复或行动]
---
3. 中等优先级列表
🟡 【中优先级】
聊天：[chat_name]
最新消息：[summary]
建议：[何时/如何回复]
---
4. 低优先级/无需关注
🟢 【低优先级/已处理】
聊天：[chat_name]
状态：[状态描述]
---
5. 统计和建议
- 哪些聊天需要立即回复
- 哪些可以稍后处理
- 哪些暂时不需要关注
智能识别规则
需要立即回复的信号
-
直接问题
- 包含 "？"
- 疑问词开头：什么、哪、怎么、能不能等
-
请求和邀约
- "能帮我..."
- "你有空吗..."
- "我们..."（邀约）
-
确认事项
- "好吗？"
- "可以吗？"
- "行吗？"
-
时间敏感
- 提到具体时间
- "今天"、"明天"、"马上"
- "截止"、"之前"
可以稍后回复的信号
-
分享类
- "给你看..."
- "分享一个..."
- 转发的文章、链接
-
状态更新
- "我刚..."
- "我在..."
- 日常生活分享
-
群聊中已有他人回复
- 群聊消息已有其他人响应
- 话题已由他人接续
无需回复的信号
-
单向通知
- 系统消息
- 纯粹的信息告知
-
对话已结束
- "好的"、"嗯嗯"等结束语
- 话题自然收尾
-
自言自语
- 表情符号
- 非针对性的感叹
特殊场景处理
场景 1：群聊过滤
在群聊中：
- 识别 @ 当前用户的消息（高优先级）
- 识别与用户相关的话题
- 过滤无关的群聊水消息
场景 2：多条未读消息
当某个聊天有多条未读：
- 综合理解整个对话流
- 识别最后一条是否需要回复
- 标注对话的演变过程
场景 3：重要联系人优先
如果用户指定了优先关注的人或关键词：
- 这些聊天的消息自动提升优先级
- 单独标注为重点关注
场景 4：检测重复催促
识别对方多次询问同一问题：
- 标记为高优先级
- 提示用户可能需要尽快回复
高级功能
1. 关键词监控
用户可以设置关键词，包含这些词的消息自动高优先级：
- 工作相关："项目"、"会议"、"汇报"
- 重要人物名字
- 特定话题
2. 模式识别
识别消息模式：
- 连续多条未回复（可能被忽略了）
- 问候开场（可能有后续请求）
- 铺垫性对话（可能要说重要的事）
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.
- 8d ago First seen · 277 lines · 38 tokens per session scan A a7da7c76fe5c
multi-chat-checker is an agent published in the GitHub repository zbvxbb622-code/wechat-mcp-friend-automation (0 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,939 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to multi-chat-checker, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
code-reviewer
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy.
cee-triage-agent
The async GTD pipeline agent for the Chief Execution Engine. Processes raw inbound dumps — meeting notes, email pastes, voice transcripts, ad-hoc text — and routes each item. Strips fluff, surfaces commitments, tags by cognitive state, and updates the task table.
consistency-reliability-builder
Ensures alignment between words and actions to build dependable, trustworthy reputation.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.