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 zjp1997720/zhijian-skills --skill html-expressgit clone --depth 1 https://github.com/zjp1997720/zhijian-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/zjp1997720/zhijian-skills/html-express)<a href="https://agentmods.dev/skills/zjp1997720/zhijian-skills/html-express"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/html-express/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/zjp1997720/zhijian-skills/html-express"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/html-express.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 | $0.00128 | $0.01278 |
| Opus 5.5 | $0.00051 | $0.00511 |
| Sonnet 5.5 | $0.00026 | $0.00256 |
| Haiku 4.5 | $0.00013 | $0.00128 |
Grade A, and why
html-express 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 29d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- html-express — 100% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
html-express
Agent 的日常 HTML 表达层。当信息密度高、读者要费力扫读时，用单个自包含 HTML 代替 Markdown。
灵感：Anthropic《Using Claude Code: The unreasonable effectiveness of HTML》—— HTML 是 Agent 最好的表达介质。
为什么是 HTML 不是 Markdown
- 信息密度：HTML 能做结构、对比、交互，Markdown 只能堆文本
- 可读性：表格、指标、时间线用 Markdown 是灾难，用 HTML 是享受
- 自包含：一个文件，双击即开，零运行环境，可分享
- 判断准则：读者要「费力扫读」的，升 HTML；一句话能说清的，留 Markdown
路由：该不该用 html-express
| 信号 | 去哪 |
|---|---|
| 要 PDF / 简历 / PPT / 落地页 / 白皮书 | → kami |
| 要视频 / 动画 / 字幕 / 转场 | → hyperframes |
| 要把大段信息整理成一页可读的网页 | → 本 skill |
| 一句话能说清的结论 | → 直接回 Markdown |
组件清单（10 个）
| 组件 | 适合什么信息 |
|---|---|
metric-card |
关键指标、数据看点（2-4 个并排） |
comparison-table |
多方案横向对比 |
data-table |
结构化数据罗列（非对比） |
timeline |
时间线、里程碑、路线图 |
checklist |
步骤、SOP、检查项 |
quote-card |
判断、原话、金句 |
code-block |
代码、命令、配置 |
details |
长内容折叠（零 JS） |
badge |
状态标签（成功/警示/中性） |
columns |
多视角并置、优劣势对照 |
源码在 assets/components/。骨架在 assets/skeleton.html，token 在 assets/tokens.css。10 个组件的完整效果见 assets/demo-all.html（双击打开）。
组装流程
- 识别信息形态 → 对比？清单？指标？时间线？引用？决策？
- 选组件 → 从清单挑 2-5 个最配的，不强求全用
- 套骨架 → 复制
assets/skeleton.html，把tokens.css完整内容粘进顶部<style>（替换@import） - 填内容 → 数据 > 形容词；不留占位符；缺数据标
[数据待补：说明] - 产出 → 单个
.html，双击即开
信息形态 → 组件 路由表
| 信息形态 | 推荐组件 |
|---|---|
| 多方案横向对比 | comparison-table + badge |
| 关键指标 / 数据看点 | metric-card（2-4 个并排） |
| 时间线 / 里程碑 / 路线图 | timeline |
| 步骤 / SOP / 清单 | checklist |
| 大段判断 / 原话 / 金句 | quote-card |
| 代码 / 命令 / 配置 | code-block |
| 长内容折叠 | details |
| 结构化数据罗列 | data-table |
| 多视角并置 | columns |
视觉契约（绑定 智见AI DESIGN.md）
token 已在 assets/tokens.css 抽好，组件一律引用变量，不要写死颜色/字号字面值。
- 背景永远暖纸
#F5F4ED，不纯白 - 主行动色暖陶
#B85235，结构色墨蓝#1B365D - 正文链接用
--accent-text（#A04A2E，对比度安全） --human（#C96442）只做装饰或 ≥22px 大字，不可做正文小字（对比度仅 3.7:1）- 字体靠 fallback，不嵌入字体文件
禁止（Agent 最容易犯的）
- ❌ 占位符残留（
[填这里]、Lorem、TBD） - ❌ 编造数据、统计；缺数据标
[数据待补：说明] - ❌ 弱表格——该用对比矩阵却堆成清单
- ❌ 渐变、玻璃拟态、霓虹、强阴影（DESIGN.md 明令禁止）
- ❌ 做成营销落地页（那是 kami 的事）
What ships with it
15 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.
- agents/openai.yaml 280 B
- assets/components/badge.html 1.2 KB
- assets/components/checklist.html 1.4 KB
- assets/components/code-block.html 1.2 KB
- assets/components/columns.html 1.1 KB
- assets/components/comparison-table.html 1.7 KB
- assets/components/data-table.html 1.2 KB
- assets/components/details.html 1.3 KB
- assets/components/metric-card.html 1.3 KB
- assets/components/quote-card.html 1.0 KB
- assets/components/timeline.html 1.7 KB
- assets/demo-all.html 17 KB
- assets/skeleton.html 2.3 KB
- assets/tokens.css 3.5 KB
- LICENSE 1.0 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.
- 29d ago Changed · +3 lines 430efafef804
- 2mo ago First seen · 89 lines · 128 tokens per session scan A dbd9889900a4
html-express is a skill published in the GitHub repository zjp1997720/zhijian-skills (787 stars, last pushed 4d ago), licensed MIT. It adds 128 tokens to every session and 1,278 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 2026-08-30.
html-express compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| html-expresszjp1997720/zhijian-skills | Skill | 787 | 4d ago | MIT | A | 128 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| ppt-reviewOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 2 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |