Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add caigee-cmd/wechat-insight --skill analyzing-wechat-chatsgit clone --depth 1 https://github.com/caigee-cmd/wechat-insightWrote 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/caigee-cmd/wechat-insight/analyzing-wechat-chats)<a href="https://agentmods.dev/skills/caigee-cmd/wechat-insight/analyzing-wechat-chats"><img src="https://agentmods.dev/badge/skills/caigee-cmd/wechat-insight/analyzing-wechat-chats.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.02776 |
| Opus 5 | $0.00048 | $0.01388 |
| Sonnet 5 | $0.00019 | $0.00555 |
| Haiku 4.5 | $0.00010 | $0.00278 |
Grade C, and why
analyzing-wechat-chats scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
> curl -sL https://raw.githubusercontent.com/caigee-cmd/wechat-insight/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> curl -sL https://raw.githubusercontent.com/caigee-cmd/wechat-insight/main/install.sh | bash This is a copy
92% identical to analyzing-wechat-chats — 23 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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
分析微信聊天记录 Analyzing WeChat Chats
前置依赖：本 skill 不是自包含的，运行需要
./wechat-insightCLI（仓库：https://github.com/caigee-cmd/wechat-insight）。触发本 skill 时按以下顺序判断当前 CLI 位置：
- 当前目录有
wechat-insight可执行文件 → 直接用./wechat-insight ...~/.local/share/wechat-insight/wechat-insight存在 →cd ~/.local/share/wechat-insight后用./wechat-insight ...- 都没有 → 提示用户、并提议执行一行安装（macOS only）：
脚本会 clone 仓库到curl -sL https://raw.githubusercontent.com/caigee-cmd/wechat-insight/main/install.sh | bash~/.local/share/wechat-insight、创建 venv、安装 Python 依赖。装好后再cd进去触发本 skill。./wechat-insightlauncher 会自动使用.venv，不需要手动source activate。
总览
这是一个 本地微信分析工作台 v1。
当前已经可用的能力：
- feature 层生成
- Markdown 日报
- 面向自动化宿主的一键 digest 日报
- 客户 / 商业分析
- 联系人标签模板生成与自动建议
- 单文件 HTML 报告（默认叙事版滑动年报，纯 Python 渲染，不依赖 Node）
- 可分享的竖版关系画像卡
启发式分析能力（基于聊天文本的统计规则推测，不是医学诊断、心理测评或模型级结论，结果仅供参考）：
- 情绪分析
- MBTI 推测
- 口癖统计
- 社交图谱
适用条件
- macOS
- 微信 Mac 4.x 已安装并登录过
- Python 3.9+
核心原则
- 优先使用统一 CLI：
./wechat-insight - 首次使用先跑
doctor - 分析类请求尽量走：
featuresdailylabelscustomer
- 对启发式分析能力，必须明确告知“仅供参考”，不要包装成模型级结论
当前命令面
| 命令 | 作用 | 状态 |
|---|---|---|
./wechat-insight doctor |
检查配置状态 | 可用 |
./wechat-insight features |
生成 feature 层 | 可用 |
./wechat-insight daily |
生成日报 | 可用 |
./wechat-insight labels |
生成联系人标签模板 | 可用 |
./wechat-insight customer |
生成客户 / 商业分析 | 可用 |
./wechat-insight report-data |
汇总展示层统一 JSON 载荷 | 可用 |
./wechat-insight html |
生成本地可打开的单文件 HTML 报告（默认叙事版滑动年报） | 可用 |
./wechat-insight share |
生成可分享的竖版关系画像卡 | 可用 |
./wechat-insight emotion |
情绪分析（启发式） | 可用 |
./wechat-insight mbti |
MBTI 推测（启发式） | 可用 |
./wechat-insight speech |
口癖统计（启发式） | 可用 |
./wechat-insight social |
社交图谱（启发式） | 可用 |
标准执行流
Phase 1: 环境检查
每次优先执行：
./wechat-insight doctor
判断逻辑：
- 配置完整：进入具体任务
- 配置缺失：进入首次配置
Phase 2: 首次配置
./wechat-insight setup
脚本会自动：
- 检查微信环境
- 自动识别
wxid和数据库路径 - 生成：
~/.config/wechat-insight.json
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 · 410 lines · 97 tokens per session scan C 133edabdfdc3
analyzing-wechat-chats is a skill published in the GitHub repository caigee-cmd/wechat-insight (137 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 2,776 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). It is 92% identical to analyzing-wechat-chats, differing in 23 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…