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 eiway112/prefab-interior-skills --skill scanned-standard-clause-verifygit clone --depth 1 https://github.com/eiway112/prefab-interior-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/eiway112/prefab-interior-skills/scanned-standard-clause-verify)<a href="https://agentmods.dev/skills/eiway112/prefab-interior-skills/scanned-standard-clause-verify"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/scanned-standard-clause-verify/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/eiway112/prefab-interior-skills/scanned-standard-clause-verify"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/scanned-standard-clause-verify.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 | $0.00114 | $0.03022 |
| Opus 5 | $0.00057 | $0.01511 |
| Sonnet 5 | $0.00023 | $0.00604 |
| Haiku 4.5 | $0.00011 | $0.00302 |
Grade A, and why
scanned-standard-clause-verify scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 建标库：WebFetch 重定向死循环 → `curl -A <UA>` 直抓 How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
标准条文核验流水线（scanned-standard-clause-verify）
定位
把"某标准某条文"从"声称存在"核验到"S1 级确认属实"的可重复流水线。源于装配式装修技能合集的官方核验实践（T/CECS 1018-2022、SJG 159-2024、DB33/T 1259-2021 等案例）。
S1 判定两要素：官方发布 + 官方文本核验。两要素齐备才标 S1；缺任一要素只能标"待官方核验"，且不得单独支撑安全类 pass 结论。
输入
- 标准编号（必需）
- 本地官方出版物 PDF 或官方发布渠道线索（必需其一）
- 待核验引用点清单（条文号/术语/限值/公式，可后续补充）
步骤
Step 1 身份核验
从官方出版物核验六要素：公告号（如有）、发布机构、发布日期、实施日期、主编单位、出版信息。
- 日期优先级：PDF 封面 > 官方在线平台（如 openstd、全国标准信息公共服务平台）。封面与在线冲突时以封面为准。
- 扫描版 PDF 用 PyMuPDF 渲染（dpi≥150）后用 Read 视觉读取封面/公告页；文本版直接提取。
Step 2 版本形态判定
- 强水印重复出现 ≥3 次 → 判扫描版；辅助判据：可提取中文字符数异常低、机构名比例异常。
- 文本版注意：目录顺序可能与正文不一致，引用条目编号以正文实际出现位置为准。
Step 3 提取路径选择
| 形态 | 路径 |
|---|---|
| 文本版 | pdfplumber 直接提取 |
| 扫描版 | PyMuPDF dpi≥150 渲染 + Read 视觉读取（首选，T/CECS 案例验证有效）；大篇幅再考虑 OCR 分块 |
| 目次页偏移 | 目录页码常与 PDF 物理页不一致：先用一条已知条文定位实际页，算出偏移量再批量定位 |
Step 4 官方文本缺失时的二手源降级链
仅当无官方文本可用时启用，且须两源印证：
- 知乎转载页：WebFetch 返 403 →
chrome.exe --headless=new --dump-dom+ UA 伪装 +--virtual-time-budget抓全文 - 建标库：WebFetch 重定向死循环 →
curl -A <UA>直抓 - 头条系：反爬严格，WebFetch 只返回验证脚本 → 浏览器自动化（open tab → navigate → get_page_text）
- 地方标准：优先找住建局官方发布 PDF（SJG 159-2024 案例即此路径，官方发布 PDF 即满足 S1 两要素）
Step 5 引用点逐条核对
每个待核验点输出核对表：条文号 | 核验内容 | 原文摘录 | 页码/位置 | 结论（一致/不一致/不存在）。"不存在"的条文号（如臆造条文）必须显式记录并全链删除。
Step 6 分级标注与登记
- 结论写入 standards-index（项目仓
_专题_技能合集策划/standards-index.md）：核验记录表新增行 + 状态字段更新 + §八变更日志。 - 在 change-governance.md 登记变更编号（CG-YYYYMMDD-序号），级别按该文件第一节判定。
- 入库/重编号须按 prefab-governance-sync 技能的发布流程同步三层（项目仓 → 运行时根 → shared 镜像）。
Step 7 标注全链清除（核验完成后）
对活跃文件（combined_reference / SKILL.md / examples.md / 运行时技能文件）按下列变体模式清单逐一 grep 并清除；技能升版号（x.y.z 第三位）。
变体模式清单（实测出现过的变体，须全部执行，漏一项即残留）：
| 模式 | 实际形态示例 |
|---|---|
| 待官方核验 | 〔待官方核验〕降级标注 |
| 条文号待核验 | 〔S1·条文号待核验〕 |
| 待核验条文号 / 待补录标准 | "未决事项"表行 |
| 未对全文核验 | "条文号/表号/具体条文未对全文核验" |
清除边界：Step 7 只清技能内容文件中的降级标注；standards-index 的核验状态字段与备注（如"待核验""待补充官方来源"）属索引记录，由 Step 6 更新，不在清除范围。裸词"待核验"不得作为清除模式——它是索引 schema 的合法状态枚举值（interface-contracts verification_status），裸匹配会误伤治理文件。
零断言验收：清除后对清单中每个模式在活跃文件范围重新 grep，须全部零命中；任一残留即视为清除未完成。
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.
- 12d ago First seen · 156 lines · 114 tokens per session scan A e2af60536cbb
scanned-standard-clause-verify is a skill published in the GitHub repository eiway112/prefab-interior-skills (4 stars, last pushed 11d ago), licensed MIT. It adds 114 tokens to every session and 3,022 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
software-certificate-skill
An automated workflow for preparing Chinese software-copyright registration materials from a real software project. It produces application information, an operation manual, and source-code documents with evidence from the project.