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 fangshui-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/fangshui-bikeng-zhinan)<a href="https://agentmods.dev/skills/zx029w/zhuangxiu-skills/fangshui-bikeng-zhinan"><img src="https://agentmods.dev/badge/skills/zx029w/zhuangxiu-skills/fangshui-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/fangshui-bikeng-zhinan"><img src="https://agentmods.dev/badge/skills/zx029w/zhuangxiu-skills/fangshui-bikeng-zhinan.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 | $0.00116 | $0.01586 |
| Opus 5.5 | $0.00046 | $0.00634 |
| Sonnet 5.5 | $0.00023 | $0.00317 |
| Haiku 4.5 | $0.00012 | $0.00159 |
Grade A, and why
fangshui-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 28d 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.
What it actually says
防水避坑指南
防水是隐蔽工程里最不能省、最怕返工的一环。漏了不是砸砖就是赔楼下，代价极大。本 Skill 把西安装修课堂知识库里防水专题的精华按倒序（最新在前）整理，覆盖卫生间、阳台、厨房、屋面外墙、地下室的防水做法、材料选择、细部处理和闭水验收全链路避坑。
核心原则（先记住这 5 条）
- 防水先算范围：湿区（卫生间、阳台、厨房）必须做，干区别乱刷，门口和管根阴角是重点。
- 材料别瞎选：卫生间用柔性防水（JS/聚氨酯），屋面用卷材，刚柔分工明确。
- 遍数和高度到位：墙面防水刷够高度（淋浴区1.8米起），地面两遍以上，别省遍数。
- 闭水试验不能跳：做完必须蓄水24-48小时，到楼下看天花，确认不漏再贴砖。
- 渗漏维修先找源：别一漏就刷表面，先定位是管根、裂缝还是门槛，对症处理。
分主题速查
- 阳台厨房防水：ref-003（厨房地漏要留吗？需要做防水吗？）、ref-004（阳台到底怎么改造利用？封不封窗、做家政区还是休闲区、配重墙能不能拆、防水怎么做？）
- 渗漏与维修：ref-006（水电与渗漏问题急救）、ref-007（邻居装修侵权怎么办（漏水泡了自家、破坏承重、遮挡采光），维权路径是什么？）、ref-008（断桥铝门窗怎么选，怎么避免花了大价钱还是漏风、漏水、隔音差？）
- 闭水与验收：ref-005（收房验房和阶段验收怎么做？空鼓、平整度、闭水试验、水电打压怎么逐项把关？）
- 其他：ref-001（为什么防水怎么做，才是正确的？）、ref-002（防水避坑指南）、ref-009（2025-2026年装修流程新标准与工期管理）、ref-010（水电改造与瓦工阶段）、ref-011（知道水电 40 条，装修开始就容易了）、ref-012（11个装修项目，做法不同，代价天差地别）、ref-013（厨卫单项费用）、ref-014（厨卫翻新类）、ref-015（老房改造2025-2026新趋势与省钱新招）、ref-016（这8个'多此一举'的设计，做了反而更省钱！）、ref-017（选公司与合同避坑）、ref-018（买房避坑类）、等
使用方法
用户问相关空间装修问题（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、改下水），一定提醒先确认是否非承重墙、物业政策、防水范围。
- 涉及安全（用电、防滑、儿童安全），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（共 26 篇，倒序）
- ref-001.md — 为什么防水怎么做，才是正确的？
- ref-002.md — 防水避坑指南
- ref-003.md — 厨房地漏要留吗？需要做防水吗？
- ref-004.md — 阳台到底怎么改造利用？封不封窗、做家政区还是休闲区、配重墙能不能拆、防水怎么做？
- ref-005.md — 收房验房和阶段验收怎么做？空鼓、平整度、闭水试验、水电打压怎么逐项把关？
- ref-006.md — 水电与渗漏问题急救
- ref-007.md — 邻居装修侵权怎么办（漏水泡了自家、破坏承重、遮挡采光），维权路径是什么？
- ref-008.md — 断桥铝门窗怎么选，怎么避免花了大价钱还是漏风、漏水、隔音差？
- ref-009.md — 2025-2026年装修流程新标准与工期管理
- ref-010.md — 水电改造与瓦工阶段
- ref-011.md — 知道水电 40 条，装修开始就容易了
- ref-012.md — 11个装修项目，做法不同，代价天差地别
- ref-013.md — 厨卫单项费用
- ref-014.md — 厨卫翻新类
- ref-015.md — 老房改造2025-2026新趋势与省钱新招
- ref-016.md — 这8个'多此一举'的设计，做了反而更省钱！
- ref-017.md — 选公司与合同避坑
- ref-018.md — 买房避坑类
- ref-019.md — 梅雨季装修后家里返潮发霉，怎么从源头防潮、除湿、调节室内微气候？
- ref-020.md — 淘汰红线项清单（一）：12句假忠告与信息差
- ref-021.md — 瓷砖与墙面问题补救
- ref-022.md — 施工环节偷项漏项
- ref-023.md — 选装修公司类
- ref-024.md — 选公司与筛选技巧（三）：四步淘汰法与进阶技巧
- ref-025.md — 装修避坑问答2025-2026新问题中新答案
- ref-026.md — 这5处装修别随便自己动手，看似省钱，实则返工更贵
What ships with it
27 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.
- .gitkeep 1 B
- references/ref-001.md 3.0 KB
- references/ref-002.md 5.5 KB
- references/ref-003.md 1.5 KB
- references/ref-004.md 2.8 KB
- references/ref-005.md 2.3 KB
- references/ref-006.md 3.5 KB
- references/ref-007.md 2.7 KB
- references/ref-008.md 2.4 KB
- references/ref-009.md 6.4 KB
- references/ref-010.md 4.2 KB
- references/ref-011.md 5.1 KB
- references/ref-012.md 11 KB
- references/ref-013.md 5.3 KB
- references/ref-014.md 4.3 KB
- references/ref-015.md 4.9 KB
- references/ref-016.md 10 KB
- references/ref-017.md 24 KB
- references/ref-018.md 6.7 KB
- references/ref-019.md 2.6 KB
- references/ref-020.md 7.6 KB
- references/ref-021.md 3.6 KB
- references/ref-022.md 11 KB
- references/ref-023.md 4.8 KB
- references/ref-024.md 6.3 KB
- references/ref-025.md 4.7 KB
- references/ref-026.md 10 KB
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.
- 28d ago First seen · 61 lines · 116 tokens per session scan A acad27021069
fangshui-bikeng-zhinan is a skill published in the GitHub repository zx029w/zhuangxiu-skills (85 stars, last pushed 5d ago), licensed MIT. It adds 116 tokens to every session and 1,586 once invoked, about $0.0005 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 2026-09-29.
Other skills, from other repositories
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-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-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…