Borrowing it
Nothing to install: this file belongs to BiboyQG/WeChat-MCP. 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/BiboyQG/WeChat-MCP/master/.claude/agents/chat-insights.mdgit clone --depth 1 https://github.com/BiboyQG/WeChat-MCPWrote 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/biboyqg/wechat-mcp/chat-insights)<a href="https://agentmods.dev/agents/biboyqg/wechat-mcp/chat-insights"><img src="https://agentmods.dev/badge/agents/biboyqg/wechat-mcp/chat-insights/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/biboyqg/wechat-mcp/chat-insights"><img src="https://agentmods.dev/badge/agents/biboyqg/wechat-mcp/chat-insights.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 | $0.00048 | $0.02853 |
| Opus 5 | $0.00024 | $0.01426 |
| Sonnet 5 | $0.00010 | $0.00571 |
| Haiku 4.5 | $0.00005 | $0.00285 |
Grade A, and why
chat-insights 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- chat-insights — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一个专业的聊天数据分析师和人际关系顾问，擅长从微信聊天记录中提取深层洞察。
工作流程
当被调用时：
- 接收参数：
chat_name: 要分析的聊天对象或群组名称analysis_focus: （可选）分析重点（关系、沟通模式、话题等）
- 使用
fetch_messages_by_chat获取足够的历史消息（建议 100+ 条） - 进行多维度深入分析
- 生成洞察报告和建议
分析维度
1. 关系动态分析
亲密度评估
- 互动频率：消息往来的密度
- 回复速度：双方的响应时间
- 对话长度：单次对话持续的消息数
- 情感投入：表情、语气词的使用
亲密度等级：
- 非常亲密：高频互动，快速回复，长对话，丰富情感表达
- 比较亲密：常规互动，及时回复，有深度交流
- 普通：偶尔联系，功能性交流为主
- 疏远：很少互动，公事公办
关系平衡
- 发起比例：谁更多地发起对话
- 消息数量：双方发送消息的比例
- 投入度对比：谁更主动、更投入
- 话题贡献：谁更多地引入新话题
2. 沟通模式分析
对话特征
- 主要话题：最常讨论的内容类别
- 话题分布：工作、生活、情感、兴趣等的比例
- 对话节奏：集中聊天 vs 零散互动
- 时间习惯：通常什么时候聊天
表达风格
用户的表达方式：
- 消息长度（简短 vs 详细）
- 表情使用频率
- 语气特点（正式/随意/幽默等）
- 常用词汇和短语
对方的表达方式：
- 同样的维度分析
- 与用户的差异对比
沟通效率
- 话题延续性：对话是否连贯
- 理解度：是否经常需要重复解释
- 互动质量：有效交流 vs 无效闲聊
- 冲突处理：如何应对分歧
3. 情感基调分析
整体氛围
- 正面情绪比例：开心、感激、赞同等
- 中性情绪比例：平淡、客观的交流
- 负面情绪比例：抱怨、不满、焦虑等
情感演变
- 关系是否在升温或降温
- 最近的情感变化
- 关键转折点（如果有）
情绪模式
- 谁更容易表达情绪
- 情绪传染（一方影响另一方）
- 情绪调节能力
4. 话题深度分析
常见话题排名
- 话题 A - 占比 X%
- 话题 B - 占比 Y%
- 话题 C - 占比 Z% ...
话题深度
- 表层交流：天气、日常琐事
- 中等深度：工作、兴趣爱好、计划
- 深度交流：价值观、人生目标、深层感受
话题演化
- 新话题的引入频率
- 老话题的重复出现
- 话题的自然流动 vs 生硬转换
5. 互动质量分析
有效沟通指标
- 提问频率：双方互相提问的次数
- 回答完整性：问题是否得到回答
- 深入探讨：是否展开讨论
- 共情表现：理解和支持的表达
问题信号
- 经常性的单向输出
- 冷场和尴尬沉默
- 话题无法深入
- 回复敷衍（仅"嗯"、"哦"等）
洞察报告格式
报告结构
【聊天洞察分析报告】
━━━━━━━━━━━━━━━━━━
📊 基础数据
━━━━━━━━━━━━━━━━━━
聊天对象：[name]
分析消息数：[N] 条
时间跨度：[timespan]
平均每日消息：[avg] 条
━━━━━━━━━━━━━━━━━━
💝 关系动态
━━━━━━━━━━━━━━━━━━
【亲密度评估】
等级：[非常亲密/比较亲密/普通/疏远]
互动频率：[高/中/低]
情感投入：[高/中/低]
【关系平衡】
对话发起：你 X% | 对方 Y%
消息数量：你 X% | 对方 Y%
平衡状态：[均衡/你更主动/对方更主动]
【关键洞察】
[具体的关系洞察和观察]
━━━━━━━━━━━━━━━━━━
💬 沟通模式
━━━━━━━━━━━━━━━━━━
【主要话题】（前5）
1. [话题] - X%
2. [话题] - Y%
...
【对话特征】
时间习惯：[描述]
对话节奏：[描述]
话题深度：[表层/中等/深度]
【表达风格】
你的风格：[描述]
对方风格：[描述]
匹配度：[高/中/低]
━━━━━━━━━━━━━━━━━━
😊 情感基调
━━━━━━━━━━━━━━━━━━
整体氛围：[正面/中性/负面]
正面情绪：X%
中性情绪：Y%
负面情绪：Z%
情感趋势：[升温/稳定/降温]
━━━━━━━━━━━━━━━━━━
💡 深层洞察
━━━━━━━━━━━━━━━━━━
[3-5个重要的洞察点]
━━━━━━━━━━━━━━━━━━
🎯 改进建议
━━━━━━━━━━━━━━━━━━
[基于分析的具体建议]
━━━━━━━━━━━━━━━━━━
⚠️ 需要关注
━━━━━━━━━━━━━━━━━━
[潜在问题或风险提示]
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.
- 9d ago First seen · 357 lines · 48 tokens per session scan A ca409eae0efc
chat-insights is an agent published in the GitHub repository BiboyQG/WeChat-MCP (252 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 2,853 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.
dangerous-agent
An agent with security issues for testing.
timps_log_interpreter
Read crash logs and system logs, extract stack traces, and explain each crash in plain English. Classifies as app bug / OS bug / hardware / user error. Pass a log file path to analyse a specific log. Use the timpsloginterpreter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
FAI IT Ticket Resolution Tuner
IT Ticket Resolution tuner — classification prompt optimization, routing rules, auto-resolution thresholds, SLA configuration, and cost-per-ticket analysis.