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 Azhi-ss/html-effectiveness --skill 01-exploregit clone --depth 1 https://github.com/Azhi-ss/html-effectivenessWrote 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/azhi-ss/html-effectiveness/01-explore)<a href="https://agentmods.dev/skills/azhi-ss/html-effectiveness/01-explore"><img src="https://agentmods.dev/badge/skills/azhi-ss/html-effectiveness/01-explore/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/azhi-ss/html-effectiveness/01-explore"><img src="https://agentmods.dev/badge/skills/azhi-ss/html-effectiveness/01-explore.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 | $0.00092 | $0.01865 |
| Opus 5.5 | $0.00037 | $0.00746 |
| Sonnet 5.5 | $0.00018 | $0.00373 |
| Haiku 4.5 | $0.00009 | $0.00186 |
Grade A, and why
html-effectiveness-explore 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 2mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
01-explore — 探索与规划
"You're not sure what you want yet. Ask the agent to fan out across several directions and lay them next to each other so you can point at one."
何时用
| 用户说 | 用哪个范式 | 模板 |
|---|---|---|
| "几种实现方式给我看看 / 哪种更好" | 三方案对比 | ../templates/compare.html |
| "compare X vs Y vs Z" | 同上 | 同上 |
| "我想要 UI 但说不清风格 / 几个方向给我看" | 视觉设计方向 | 自建(见下) |
| "做一份实现计划 / RFC / 怎么落地" | 实现计划 | ../templates/plan.html |
| "ship in 2 weeks 怎么排" | 同上 | 同上 |
范式 1.1 · 三方案对比
空间形状:每个方案 = 一个完整代码块 + 一张 Pro/Con 表 + 一行指标(bundle / 可测试性 / SSR / 复用)。三个方案要并排才能比较,markdown 只能上下堆。
最少要素:
- 至少 2、不超过 4 栏(多了用户记不住)
- 每栏一段最小可运行代码(5-15 行)
- Pro/Con 各 3 条,具体(不是 "easy to read",而是 "Single import reused across filter, command bar, and board search")
- 一行指标用同一组维度,便于横向比较
- 文末一段 agent 的推荐(不要让用户全自己判断)
HTML 骨架:
<div class="approaches">
<article class="approach">
<header><span class="tag">Approach 1</span><h2>Inline useEffect</h2></header>
<pre><code>...实际可运行代码...</code></pre>
<table class="proscons">
<thead><tr><th>Pro</th><th>Con</th></tr></thead>
<tbody><tr><td>...</td><td>...</td></tr></tbody>
</table>
<footer class="metrics">
<span>Bundle <b>+0 kb</b></span>
<span>Test <b>medium</b></span>
<span>Reuse <b>low</b></span>
<span>SSR <b>yes</b></span>
</footer>
</article>
<!-- 重复 2-3 次 -->
</div>
<aside class="recommendation"><strong>建议:</strong>...</aside>
关键 CSS:
.approaches { display: grid; grid-template-columns: repeat(3, 1fr); gap: 24px; }
.approach { display: flex; flex-direction: column; gap: 16px;
padding: 20px; border: 1px solid var(--gray-300);
border-radius: 12px; background: var(--white); }
.approach pre { flex: 1; max-height: 360px; overflow: auto; }
.proscons td:first-child { color: var(--success); }
.proscons td:last-child { color: var(--danger); }
.metrics { display: flex; gap: 16px; flex-wrap: wrap;
font-size: 13px; color: var(--gray-700); }
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.
- 2mo ago First seen · 157 lines · 92 tokens per session scan A ed2adc22c9c3
html-effectiveness-explore is a skill published in the GitHub repository Azhi-ss/html-effectiveness (7 stars, last pushed 5mo ago), licensed MIT. It adds 92 tokens to every session and 1,865 once invoked, about $0.0004 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 2026-08-31.
html-effectiveness-explore compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| html-effectiveness-exploreAzhi-ss/html-effectiveness | Skill | 7 | 5mo ago | MIT | A | 92 | Claude Code, Codex |
| cinematic-scrollMustBeSimo/cinematic-scroll-skill | Skill | 34 | 1mo ago | MIT | A | 78 | Claude Code |
| cinematic-scrollMustBeSimo/cinematic-scroll-skill | Skill | 34 | 1mo ago | MIT | A | 78 | Claude Code, Codex |
| macos-26-designjuanlara-aidev/macos-26-design | Skill | 7 | 5mo ago | none | A | 154 | Claude Code |
| brand-landingpagewshobson/agents | Skill | 42k | yesterday | MIT | A | 112 | Claude Code |
| wcag-audit-patternswshobson/agents | Skill | 42k | yesterday | MIT | A | 45 | Claude Code |
| visual-qacode-yeongyu/oh-my-openagent | Skill | 71k | yesterday | none | A | 78 | Claude Code, Codex |