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 agentmods add skills/wechat-miniprogram/ai-mode-demo/drink-skillnpx skills add wechat-miniprogram/ai-mode-demo --skill drink-skillgit clone --depth 1 https://github.com/wechat-miniprogram/ai-mode-demoWrote 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/wechat-miniprogram/ai-mode-demo/drink-skill)<a href="https://agentmods.dev/skills/wechat-miniprogram/ai-mode-demo/drink-skill"><img src="https://agentmods.dev/badge/skills/wechat-miniprogram/ai-mode-demo/drink-skill.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 | $0.00000 | $0.02594 |
| Opus 5 | $0.00000 | $0.01297 |
| Sonnet 5 | $0.00000 | $0.00519 |
| Haiku 4.5 | $0.00000 | $0.00259 |
Grade A, and why
drink-skill 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 6d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
drink-skill WeStoreCafe 点单场景（小微 AI Handoff 模式）
本 SKILL 已适配「小微 SubAgent handoff」：对话内只展示文本回复 + 小程序卡片， 用户点击小程序卡片后 handoff 接力进入开发者业务页（接力页），在小程序内完成后续操作。 小微对话内不渲染原子组件；组件代码与
componentPath保留以便后续复用 / 小程序内 Agent 场景。
业务流程图（handoff 模式）
用户意图
│
├─ 明确关键词/品类（"拿铁"/"果汁"）─→ searchDrinks ──┐ 文本 + 小程序卡片
│ （模糊意图 keyword 留空，返回全部饮品） │ （点击 handoff 进列表页）
│ │
│ 点击卡片 → 接力页 home（首页浏览/搜索/筛选）
│ │ navigateTo（小程序内）
│ ↓
├─ 已知 drinkId（看详情）──→ selectDrink ──→ 文本 + 小程序卡片
│ 点击卡片 → 接力页 sku-picker（详情/选规格）
│ │ 加入订单 → navigateTo（小程序内）
│ ↓
├─ 新点一杯 / 换一杯（新建订单）─→ createOrder ─→ 文本 + 小程序卡片
│ 点击卡片 → 接力页 checkout（地址 + 支付，展示全部已选商品）
│ ↑
├─ 再加一杯 / 追加（已有订单）──→ addToOrder ──→ 文本 + 小程序卡片（同上，商品列表已含追加项）
│ │
├─ 删掉某杯（订单>1件）──────→ removeOrderItem ─→ 文本 + 小程序卡片（同上，商品列表已移除该项）
│ ↓
│ 完成下单（小程序内 wx.chooseAddress / wx.requestPayment）
│
└─ 对话中直接给出地址 ────→ saveAddress ──→ 文本 + 小程序卡片
点击卡片 → 接力页 checkout（预填地址，确认支付）
注：上图中
createOrder/addToOrder并非独立入口，均需先经selectDrink拿到目标饮品的 drinkId 与规格后才能调用（见「业务约束 2. 执行顺序」）。
原子接口 ↔ 接力页映射
| 接口 | 作用 | handoff.query | 接力页 pagePath |
|---|---|---|---|
| searchDrinks | 关键词搜索 / 浏览全部 | keyword=拿铁（可留空=全部） |
/pages/home/home |
| selectDrink | 饮品详情 + 规格 | drinkId=289 |
/packageDetail/pages/sku-picker |
| createOrder | 新建订单（首杯/换一杯） | orderId=xxx |
/packageDetail/pages/checkout |
| addToOrder | 追加商品到当前订单 | orderId=xxx |
/packageDetail/pages/checkout |
| removeOrderItem | 删除订单内某商品（至少保留一件） | orderId=xxx |
/packageDetail/pages/checkout |
| viewOrder | 查看当前进行中的订单 | orderId=xxx |
/packageDetail/pages/checkout |
| cancelOrder | 取消/清空整单 | 空（回首页） | /pages/home/home |
| saveAddress | 保存地址 → 结算页 | orderId=xxx |
/packageDetail/pages/checkout |
What ships with it
30 files 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.
- apis/addToOrder.js 4.3 KB runs code
- apis/cancelOrder.js 2.0 KB runs code
- apis/createOrder.js 4.2 KB runs code
- apis/removeOrderItem.js 4.1 KB runs code
- apis/saveAddress.js 3.0 KB runs code
- apis/searchDrinks.js 4.0 KB runs code
- apis/selectDrink.js 3.2 KB runs code
- apis/viewOrder.js 2.4 KB runs code
- components/drink-detail-card/index.js 2.4 KB runs code
- components/drink-detail-card/index.json 49 B
- components/drink-detail-card/index.wxml 728 B
- components/drink-detail-card/index.wxss 2.2 KB
- components/drink-not-found-card/index.js 534 B runs code
- components/drink-not-found-card/index.json 49 B
- components/drink-not-found-card/index.wxml 293 B
- components/drink-not-found-card/index.wxss 1.0 KB
- components/order-confirm-card/index.js 2.0 KB runs code
- components/order-confirm-card/index.json 49 B
- components/order-confirm-card/index.wxml 1.8 KB
- components/order-confirm-card/index.wxss 3.6 KB
- components/recommended-drinks/index.js 1.7 KB runs code
- components/recommended-drinks/index.json 49 B
- components/recommended-drinks/index.wxml 1.4 KB
- components/recommended-drinks/index.wxss 2.8 KB
- data/seed.js 10 KB runs code
- index.js 1.2 KB runs code
- mcp.json 23 KB
- utils/id.js 512 B runs code
- utils/sku.js 3.8 KB runs code
- utils/storage.js 3.3 KB runs code
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.
- 6d ago First seen · 102 lines · 0 tokens per session scan A f49e97bc4fc6
drink-skill is a skill published in the GitHub repository wechat-miniprogram/ai-mode-demo (286 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,594 tokens. 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 skills, from other repositories
nemoclaw-contributor-implement-issue
Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…