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 zx029w/zhuangxiu-skills --skill chufang-bikeng-zhinangit clone --depth 1 https://github.com/zx029w/zhuangxiu-skillsWrote 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/zx029w/zhuangxiu-skills/chufang-bikeng-zhinan)<a href="https://agentmods.dev/skills/zx029w/zhuangxiu-skills/chufang-bikeng-zhinan"><img src="https://agentmods.dev/badge/skills/zx029w/zhuangxiu-skills/chufang-bikeng-zhinan/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/zx029w/zhuangxiu-skills/chufang-bikeng-zhinan"><img src="https://agentmods.dev/badge/skills/zx029w/zhuangxiu-skills/chufang-bikeng-zhinan.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 | $0.00162 | $0.01835 |
| Opus 5.5 | $0.00065 | $0.00734 |
| Sonnet 5.5 | $0.00032 | $0.00367 |
| Haiku 4.5 | $0.00016 | $0.00184 |
Grade A, and why
chufang-bikeng-zhinan 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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
厨房避坑指南
厨房是“金厨银卫”里最核心的空间，也是装修遗憾出得最多的地方。本 Skill 把西安装修课堂知识库里厨房专题的精华按倒序（最新在前）整理成 24 篇参考，覆盖从格局、水电、橱柜、台面、水槽、收纳、砖墙、灯光、门、去家务化到安全与智商税的全链路避坑。
核心原则（先记住这 5 条）
- 功能满足是底线，别被颜值话术带偏：亮光柜门、不做吊柜、凉霸、双槽、石英石水槽……很多“高级感”做法是坑，过日子优先功能。
- 干厨房别做防水、别留地漏：没地漏才是正解，做了防水水往客厅漫才是真灾难。
- 装修前一次规划对，别靠入住后补：定制、尺寸、动线、插座、电器镶嵌，前期定好，后期补救又丑又贵。
- 普通家庭别硬上全开放：玻璃代替墙体+联动门做半开放，既通透又隔绝油烟，大多数中国家庭的最优解。
- 安全不侥幸：夺命操作、毒餐具、重金属锅，每一条都可能要命，照着自查表排查。
分主题速查
- 格局与开放/半开放：chufang-ban-kaifang.md（半开放厨房）、chufang-kaifang-houhui.md（开放厨房后悔）、chufang-zha-qiang-tonghtong.md（砸墙通透）、chufang-jinmen-jiushi-chufang.md（进门就是厨房怎么改）
- 水电 / 防水 / 地漏：chufang-dilou-fangshui.md
- 橱柜 / 柜门 / 吊顶 / 灯光：chufang-23-tiao-bukeng.md、chufang-10-ge-yihan.md、chufang-9-chu-jiawu.md、chufang-10-da-leiqu.md、chufang-ganjing-zhenxiang.md（去家务化）
- 台面 / 挡水 / 下挂：chufang-23-tiao-bukeng.md、chufang-9-chu-jiawu.md、chufang-17-yang-zhishui.md
- 水槽：chufang-shuicao-5-fa.md（5大黄金法则）、chufang-daotaoxiaoshuicao.md（岛台小水槽鸡肋）
- 收纳（高柜/超薄柜/切菜位）：chufang-gaogui-linghun.md、chufang-chaobao-gui.md、chufang-meidi-qiecai.md、chufang-10-ge-quwei-zuofa.md（10个有趣做法）
- 砖 / 墙面 / 门：chufang-23-tiao-bukeng.md、chufang-6-tiao-xuellei.md（大砖碾压小砖）、chufang-5-ju-guihua.md（5句鬼话）
- 安全（夺命/毒物/重金属）：chufang-7-da-duoming.md、chufang-7-da-duwu.md、chufang-6-da-yinxing-duwu.md、chufang-zhongshu-jinshu.md
- 智商税 / 鸡肋：chufang-17-yang-zhishui.md、chufang-8-da-jilei.md、chufang-10-da-leiqu.md
使用方法
用户问厨房相关装修问题（无论是否已开工），先按上面主题定位参考文件，再结合具体户型/预算给建议。重点：
- 给结论要直接，先说“别怎么做”，再说“该怎么做”。
- 涉及改造（砸墙、改门、开放改半开放），一定提醒先确认是否非承重墙、当地通气政策。
- 涉及安全（燃气、锅具、餐具），用自查表式清单，让用户能照着排查。
- 不去 AI 味，用西安装修课堂“过日子”的口吻，说人话、给干货。
参考文件清单（24 篇，倒序）
- chufang-10-ge-quwei-zuofa.md — 厨房10个有趣做法（2026-08）
- chufang-23-tiao-bukeng.md — 厨房23条不该犯的错（2026-08）
- chufang-dilou-fangshui.md — 厨房地漏要留吗/防水（2026-07）
- chufang-ban-kaifang.md — 半开放厨房（2026-02）
- chufang-9-chu-jiawu.md — 厨房9处装错家务活不断（2026-02）
- chufang-daotaoxiaoshuicao.md — 岛台小水槽鸡肋（2026-01）
- chufang-5-ju-guihua.md — 厨房5句鬼话千万别信（2026-01）
- chufang-jinmen-jiushi-chufang.md — 进门就是厨房怎么改（2025-09）
- chufang-kaifang-houhui.md — 开放厨房后悔（2025-10）
- chufang-10-ge-yihan.md — 厨房10个遗憾（2025-10）
- chufang-8-da-jilei.md — 厨房8大鸡肋产品（2025-10）
- chufang-7-da-duwu.md — 厨房7大毒物（2025-09）
- chufang-ganjing-zhenxiang.md — 厨房干净的真相（2025-09）
- chufang-zha-qiang-tonghtong.md — 砸墙通透（2025-07）
- chufang-7-da-duoming.md — 厨房7大夺命操作（2025-07）
- chufang-6-tiao-xuellei.md — 厨房6条血泪教训（2025-07）
- chufang-6-da-yinxing-duwu.md — 厨房6大隐形毒物（2025-07）
- chufang-gaogui-linghun.md — 高柜是收纳灵魂（2024-07）
- chufang-10-da-leiqu.md — 厨房10大雷区（2025-03）
- chufang-17-yang-zhishui.md — 厨房17样智商税（2025-08）
- chufang-zhongshu-jinshu.md — 释放重金属的锅（2025-08）
- chufang-chaobao-gui.md — 厨房超薄柜（2024-11）
- chufang-shuicao-5-fa.md — 水槽5大黄金法则（2025-03）
- chufang-meidi-qiecai.md — 没地切菜的神操作（2025-11）
What ships with it
24 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.
- chufang-10-da-leiqu.md 1.6 KB
- chufang-10-ge-quwei-zuofa.md 1.1 KB
- chufang-10-ge-yihan.md 1.6 KB
- chufang-17-yang-zhishui.md 1.3 KB
- chufang-23-tiao-bukeng.md 1.6 KB
- chufang-5-ju-guihua.md 1016 B
- chufang-6-da-yinxing-duwu.md 1.0 KB
- chufang-6-tiao-xuellei.md 1.1 KB
- chufang-7-da-duoming.md 1.3 KB
- chufang-7-da-duwu.md 1.1 KB
- chufang-8-da-jilei.md 1.2 KB
- chufang-9-chu-jiawu.md 1.1 KB
- chufang-ban-kaifang.md 1.3 KB
- chufang-chaobao-gui.md 1.1 KB
- chufang-daotaoxiaoshuicao.md 825 B
- chufang-dilou-fangshui.md 1.4 KB
- chufang-ganjing-zhenxiang.md 1.5 KB
- chufang-gaogui-linghun.md 992 B
- chufang-jinmen-jiushi-chufang.md 1.3 KB
- chufang-kaifang-houhui.md 1.1 KB
- chufang-meidi-qiecai.md 1.0 KB
- chufang-shuicao-5-fa.md 1.4 KB
- chufang-zha-qiang-tonghtong.md 1.2 KB
- chufang-zhongshu-jinshu.md 1009 B
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.
- 1mo ago First seen · 65 lines · 162 tokens per session scan A a06f4fa50f6a
chufang-bikeng-zhinan is a skill published in the GitHub repository zx029w/zhuangxiu-skills (86 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 1,835 once invoked, about $0.0006 per session on Opus 5.5. 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
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
feature-prioritisation
Aplica marcos de priorización (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) para clasificar características e items del backlog. Úsalo cuando se te pida priorizar características, clasificar un backlog, decidir qué construir a continuación, o evaluar compensaciones entre ideas competidoras. Produce una lista de…
outcome-tracker
Record the testable predictions inside a decision, then score them against reality later — so frameworks earn trust from outcomes, not vibes. Use when committing to a prioritisation, forecast, or plan (to log what it predicts), when asked to review what actually happened, or to compute how well-calibrated past RICE…