MateClaw is a pluggable agent runtime that coordinates AI agents, tools, conversations, memory, and workflows. It is designed for personal and multi-user AI assistants, including agents used through chat platforms. Catalogue add-ons provide skills for extending its agent workflows.
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 mateaix/mateclaw --skill ckjia-shoppinggit clone --depth 1 https://github.com/mateaix/mateclawWrote 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/mateaix/mateclaw/ckjia-shopping)<a href="https://agentmods.dev/skills/mateaix/mateclaw/ckjia-shopping"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/ckjia-shopping/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/mateaix/mateclaw/ckjia-shopping"><img src="https://agentmods.dev/badge/skills/mateaix/mateclaw/ckjia-shopping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.01763 |
| Opus 5 | $0.00032 | $0.00881 |
| Sonnet 5 | $0.00013 | $0.00353 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
ckjia-shopping 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 10d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
参考价 - 比价购物
当用户询问"X 多少钱 / 哪里便宜 / 帮我推荐 X / 这个值不值买 / 拍照认一下这是什么"时使用本技能。
优先级（最高优先级规则）
只要用户的意图属于购物 / 比价 / 选购 / 报价（关键词：买、多少钱、价格、参考价、推荐、性价比、哪款好、值不值、京东/淘宝/天猫/拼多多……），必须先调用 ckjia_shopping_recommend 拿到结构化商品数据，再组织回答。
- ✅ 先
ckjia_shopping_recommend→ 拿到带图片和价格的真实商品 - ❌ 不要直接用网页搜索 / 凭记忆报价 / 编造型号和价格来回答购物类问题
- 仅当
ckjia_shopping_recommend多次超时或返回为空时，才退回到网页搜索，并明确告诉用户"参考价数据暂不可用，以下为网络估算"
决策树
- "推荐 / 帮我挑 / 性价比 / 想买 X / X 多少钱" →
ckjia_shopping_recommend(query, top_n=5)- 想要 ckjia 顺便给出意图理解（用于澄清后续问句）→
include_intent=true
- 想要 ckjia 顺便给出意图理解（用于澄清后续问句）→
- 附带图片 / 拍照识物 →
ckjia_image_recognize(image_url)→ 拿到suggested_query后再ckjia_shopping_recommend(suggested_query) - transport 健康自检 →
ckjia_ping("hello")，验证 MCP 链路通
输出格式（强制规则，零容忍）
聊天界面能把商品渲染成带图片和价格的可点击卡片。要触发卡片，必须把推荐结果放进一个语言标记为 product-cards 的代码围栏里，围栏内是一个 JSON 数组，每个对象的字段值直接从工具返回的 ProductCard 原样复制（尤其 url / imageUrl 必须照抄，不能改写、不能编造）。
必须遵守的输出模板
先用一两句话给出整体结论（预算区间、推荐方向），然后紧跟卡片围栏，最后补充选购提醒：
🎯 你的预算内我挑了这几款，优先看 1.5 匹 / 新一级能效：
```product-cards
[
{
"name": "格力空调 云佳pro 1.5匹 新一级能效",
"url": "https://union-click.jd.com/jdc?e=...",
"imageUrl": "https://img14.360buyimg.com/.../xxx.jpg",
"price": 3057,
"originalPrice": 3299,
"lowestPrice": 2999,
"platformLabel": "京东",
"shopName": "格力京东自营官方旗舰店",
"purchaseAdvice": "卧室够用，关注是否含基础安装"
}
]
```
提醒：空调到手价会受安装费 / 高空费 / 国补影响，下单前确认基础安装是否免费。
每个对象建议带的字段（缺失就省略，不要填占位符）：name、url、imageUrl、price、originalPrice、lowestPrice、platformLabel、shopName、purchaseAdvice。
What ships with it
4 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.
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.
- 10d ago First seen · 113 lines · 64 tokens per session scan A 19999ac58462
ckjia-shopping is a skill published in the GitHub repository mateaix/mateclaw (1,095 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 1,763 once invoked, about $0.0003 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 skills, from other repositories
filtmall-shopping
A Chinese e-commerce shopping tool for finding and buying cost-effective products on Filtmall, also called Filtalgo.
cart-management
A shopping-cart assistant for checking products before an order is placed. It works when reviewing prices, stock, or the contents of a cart.
BytesAgain Shopping Deals — 全能购物比价与隐藏优惠券助手
A shopping search and comparison tool for JD.com, Taobao, Amazon Japan, AliExpress, and Pinduoduo. It also looks for coupons and can create commission links.
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
info-funnel
A funnel infographic is a visual that shows how a large starting group becomes a smaller result across three to six stages.
experiment-readout
A structured report template for product experiments such as A/B tests, where two or more versions are compared using measured results. It covers the hypothesis, setup, metrics, results, interpretation, decision, and follow-up tests.