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 ssmurfgg04-gif/context-m --skill industrial-archivegit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/industrial-archive)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/industrial-archive"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/industrial-archive/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/ssmurfgg04-gif/context-m/industrial-archive"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/industrial-archive.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 | $0.00000 | $0.04363 |
| Opus 5 | $0.00000 | $0.02181 |
| Sonnet 5 | $0.00000 | $0.00873 |
| Haiku 4.5 | $0.00000 | $0.00436 |
Grade A, and why
industrial-archive 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 9d 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.
This is a copy
100% identical to industrial-archive — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
industrial-archive — 工业风展品 / 产品落地页生成器
把"一段自然语言描述"变成一份单文件 HTML，效果是北欧工业典藏 / 博物馆策展感的产品落地页：
- 黑色画框中的产品大图，左右点击翻转切换
- 左侧带索引指示条的展品目录
- 右侧 4 个 meta 块（材料 / 产地 / 年代 / 尺寸）
- 顶栏跑马灯
- 点击画框或底部 CTA → 进入展品详情页（巨大斜体标题、规格表、主图、开篇大字 + 3 段散文、6 图画廊、上一件/下一件）
- 进入页有引言 splash
何时触发
用户说"做个工业风的产品落地页 / 克制之物风格的展品 / industrial-archive-gen ..."，并提供：
- 产品描述（必需）：一段散文，描述 1—N 件展品的名字、年代、产地、材料、来历
- 图片 URL（可选）：每件展品至少 1 张主图、最好 3—6 张细节图。没有也能跑（用 picsum 占位灰图）
- 风格（可选）：默认是冷调钢蓝灰，可换成 styles.md 里的预设
如果用户完全没给展品名/故事 → 必须问一次至少有哪几件展品要展示，以及大致是什么品类（容器 / 灯具 / 椅具 / 仪器 / 工具 / ...）。
如果用户只给了名字没给故事 → 自己编：每件展品都生成 1 句 lead + 3 段 prose + 4-6 行 spec。语气参考 reference.html：博物馆 wall-text 感 — 克制、具体、缓慢，不要 marketing 语言。
两种运行模式
模式 A · Claude Code / 本地（有文件系统）
- 输出：
~/Desktop/{slug}-archive.html（单文件，所有图走 URL） - 如果用户给了本地图，建议告知用户改用 URL 或自己拷到同目录后写相对路径
模式 B · GLM / 在线对话（无文件系统）
- 直接给一份完整 HTML 字符串，包在
```html代码块里 - 用户没给图 URL → 全用
https://picsum.photos/seed/{slug}-{nn}/{w}/{h}?grayscale占位 - 不要尝试访问本地文件
判断：如果你无法 Read 看到本地图片 → 默认走 B。
文件分工
| 文件 | 角色 | 怎么用 |
|---|---|---|
reference.html |
完整成品参考 — "克制之物" 4 件北欧工业藏品 | 看：lead 怎么写、prose 语气、spec 用词、tagline 格式、maker 命名 |
template.html |
空骨架 — 同样的 CSS/JS/路由，2 件示例 + 17 个 SWAP 标记 | 在它的基础上改，输出最终 HTML |
styles.md |
风格预设库 | 用户指定风格时查这份 |
README.md |
用户视角的使用说明 | 模型不用看 |
SKILL.md |
给模型看的工作流（本文件） | 必读 |
核心规则：所有改动基于 template.html；从 reference.html 学怎么写（语气、字数、词汇），但不要复制具体内容。
关键差别 — reference 用 SVG，template 用 <img>
reference.html的 4 件展品是手绘 SVG（铸铁壶 / 轴承灯 / 桦木椅 / 测距仪），那是定制内容template.html已经把 SVG 系统替换成<img src="cover URL">，用户给 URL 就用 URL，没给就用 picsum- 你不需要写 SVG。如果用户特别要求"画出来"，再考虑写一个 SVG 函数塞进
coverHTML()
工作步骤
1. 读两份 HTML
- 先读
reference.html体会"完整后长什么样"，特别是exhibits-dataJSON 的字段密度和 prose 语气（克制、具体、有时代背景） - 再读
template.html找 17 个 SWAP 标记（搜SWAP-）
不要改 JS / 不要改 CSS / 不要改详情页路由系统。 SWAP 都在 HTML 文本和 JSON 数据里。
2. 解析用户输入抽信息
全站层级（17 个 SWAP 中的 1-15、17）
- COLLECTION_TITLE / COLLECTION_SUB — 系列大标题 + 副标。如"克制之物 / 北欧工业典藏 1948—1988"。SWAP-1
- INTRO_VOLUME_TAG — 进入页顶部的 tag，如"北欧工业典藏 · Vol.01"。SWAP-2
- INTRO_TITLE_HTML — splash 页大标题，2-4 字 + 中间一个
<span class="accent">·</span>分隔符。如克制<span class="accent">·</span>之物。SWAP-3 - INTRO_TITLE_EN — splash 页英文副标，全大写 + em-dash，如
Restrained Objects — A Nordic Industrial Archive 1948 — 1988。SWAP-4 - INTRO_QUOTE — 一句策展引言，60—100 字，散文感。SWAP-5
- INTRO_ATTRIBUTION — 引言出处，如
— 策展前言 / Curatorial Note。SWAP-6 - HEAD_GLYPH — 左上 logo 字符。1-2 个 serif 字符，建议带特殊感的字母如
ÆØ沉匠ʘ。SWAP-7 - HEAD_GLYPH_SUB — logo 下一行说明，如
克制之物 / 编号 N°01—04。SWAP-8 - HEAD_CENTER_CN / HEAD_CENTER_EN — 顶部中央两行小字。SWAP-9, 10
- HEAD_RIGHT_TOP / HEAD_RIGHT_BOTTOM — 顶右两行：日期/城市 + 坐标/编号。SWAP-11, 12
- CURATOR_NAME / CURATOR_EMAIL — 策展方名称 + 邮箱。SWAP-13, 14
- CRUMB_ROOT / CRUMB_VOLUME — 详情页面包屑两个固定项。SWAP-15
- TICKER_TAIL — 跑马灯尾巴的总标语。SWAP-17
What ships with it
3 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.
- 9d ago First seen · 246 lines · 0 tokens per session scan A fe4d27942566
industrial-archive is a skill published in the GitHub repository ssmurfgg04-gif/context-m (2 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,363 tokens. A static security scan graded it A with 0 findings. It is 100% identical to industrial-archive, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
gsd-sketch
Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode).
gsd-ui-phase
Generate UI design contract (UI-SPEC.md) for frontend phases.
gsd-ui-review
Retroactive 6-pillar visual audit of implemented frontend code.
userinterface-wiki
UI/UX best practices for web interfaces. Use when reviewing animations, CSS, audio, typography, UX patterns, prefetching, or icon implementations. Covers 11 categories from animation principles to typography. Outputs file:line findings.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
frontend
Two-mode frontend skill: (1) authoring — accessibility, responsive layout, loading/error states, performance, DESIGN.md authoring, visual direction; (2) critique — READ-only scored review of built UI against anchored rubric, AI-slop detection, two isolated assessments. Router invokes mode via context.