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 agentmods add skills/azhi-ss/html-effectiveness/07-researchnpx skills add Azhi-ss/html-effectiveness --skill 07-researchgit 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/07-research)<a href="https://agentmods.dev/skills/azhi-ss/html-effectiveness/07-research"><img src="https://agentmods.dev/badge/skills/azhi-ss/html-effectiveness/07-research.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.01589 |
| Opus 5 | $0.00047 | $0.00794 |
| Sonnet 5 | $0.00019 | $0.00318 |
| Haiku 4.5 | $0.00009 | $0.00159 |
Grade A, and why
html-effectiveness-research 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 5d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
07-research — 研究与学习
"An explainer with collapsible sections, tabbed code samples and a glossary in the margin reads very differently from the same words dumped linearly. The agent can build the scaffolding that makes a new topic navigable."
何时用
| 用户说 | 用哪个范式 | 模板 |
|---|---|---|
| "rate limit 在这个 repo 里怎么工作" | 特性解释器 | 自建(见下) |
| "auth flow 是什么样的" | 特性解释器 | 同上 |
| "讲讲一致性哈希 / Raft / token bucket" | 概念解释器 | ../../templates/concept.html |
| "这是什么 / 我怎么理解 X" | 看深度 — markdown 一段或概念解释器 | — |
特性解释器 = 在这个 repo 里的具体实现(用户已在仓库内) 概念解释器 = 抽象概念(与具体仓库无关,要交互式可视化)
范式 7.1 · 特性解释器
空间形状:4 段
- TL;DR 框 — 一段话讲完核心机制 + 性能数字
- 请求路径编号步骤 — 1/2/3/4,每步可折叠看代码
- 配置 Tab 切换 — yaml / route.ts / response 三 tab 切换
- FAQ —
<details>列表
HTML 骨架:
<aside class="tldr">
<strong>TL;DR</strong>
<p>The whole path is ~40 lines and adds about 0.4 ms p50 to every request.</p>
</aside>
<h2>The request path, step by step</h2>
<ol class="steps">
<li>
<span class="num">1</span>
<h3>Identify the caller <code>middleware/ratelimit.ts:21</code></h3>
<p>The middleware reduces the request to a <code>bucketKey</code>...</p>
<details><summary>show source</summary>
<pre><code>...</code></pre>
</details>
</li>
<!-- 步骤 2-4 -->
</ol>
<h2>Configuring a limit on your route</h2>
<div class="tabs" role="tablist">
<button role="tab" data-tab="yaml" class="active">limits.yaml</button>
<button role="tab" data-tab="route">route.ts</button>
<button role="tab" data-tab="resp">response</button>
</div>
<div class="tab-panels">
<pre data-panel="yaml" class="active"><code>...</code></pre>
<pre data-panel="route" hidden><code>...</code></pre>
<pre data-panel="resp" hidden><code>...</code></pre>
</div>
<h2>FAQ</h2>
<details>
<summary>How do I exempt internal traffic?</summary>
<p>Set <code>x-acme-internal: 1</code> from the caller; the middleware checks it against mTLS peer name.</p>
</details>
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.
- 5d ago First seen · 136 lines · 94 tokens per session scan A 1fa2773bffdd
html-effectiveness-research is a skill published in the GitHub repository Azhi-ss/html-effectiveness (5 stars, last pushed 3mo ago), licensed MIT. It adds 94 tokens to every session and 1,589 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
cinematic-scroll
Build cinematic scroll-driven, 3D-tilt, parallax, and environment-morphing websites — pinned chapter reveals, hero parallax, depth-image figures, hover-tilt cards, background-morphing layouts, release/launch pages, product story pages, or editorial commerce microsites. From a single self-contained scroll section (Mode…
cinematic-scroll
Build cinematic, scroll-driven websites — pinned chapter reveals, multi-depth parallax, 3D tilt, and environment-morphing backgrounds, from a single self-contained HTML section to a full Next.js release site. The motion grammar is the constant; the aesthetic is always the user's.
paper-reading
Reads and analyzes academic papers (arXiv preprints, conference / journal PDFs, Zotero items) at three configurable depths: quick skim (2 min), standard read (10 min), or deep analysis (30 min). Produces structured digests covering problem, method, key innovation, results, limitations, reproducibility, hidden…
learn-codebase
Socratic tutor that teaches codebase understanding through questioning, challenges, and active recall. Invoke with /learn-codebase when onboarding to a new codebase or deepening understanding of existing code. Maintains a learning journal that tracks mastery and schedules reviews.
project-interview-skill
在项目根目录生成导学.md与面经.md;大厂工程向、第一人称口播(每题≥150字完整STAR)、 简历一句话简介、仓库相对路径阅读指引、量化合并文末(待测+如何测)。触发:面经、导学、 interview analyzer、项目分析、面试准备、STAR、简历亮点。.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.