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 hxy91819/mason-skills --skill reader-led-designgit clone --depth 1 https://github.com/hxy91819/mason-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/hxy91819/mason-skills/reader-led-design)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/reader-led-design"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/reader-led-design/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/hxy91819/mason-skills/reader-led-design"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/reader-led-design.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 | $0.00086 | $0.02211 |
| Opus 5.5 | $0.00034 | $0.00884 |
| Sonnet 5.5 | $0.00017 | $0.00442 |
| Haiku 4.5 | $0.00009 | $0.00221 |
Grade A, and why
reader-led-design 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
以读者任务为起点设计
先回答「谁在什么情境打开这一页,要理解或决定什么」,再决定版面;版面由证据的形状决定,不由文件类别决定。目标是判断力,不是装饰。
来源:本 skill 从 Vercel 的 design.md 提炼可迁移的方法,去掉 Vercel 品牌、vbg-* CSS API 与 Geist 字体等专属内容。共用 token、主题与元件来源由专案文件指定;原型与正式版沿用专案的共用来源,不另建平行系统。
优先序
需求冲突时依此顺序保护:
- 来源事实、公式、单位、限定条件、隐私与任务约束。
- 既有框架、路由、档案结构、专案的共用 token、主题来源与元件惯例。
- 读者的问题、最强有据答案、关键证据一眼可见。
- 针对这份素材的构图,而非模型预设版面或固定模板。
- 响应式、互动与细节,不以削弱层次为代价。
只有在继续做会改变商业含义、法律或安全主张、隐私、公式、单位、母体、期间、客户身分、建议、核准、期限、负责人或行动呼吁时,才集中问一组问题;否则略去未知、如实标示,继续。
四个阶段
1. 厘清读者任务
看完全部素材再动手。私下确立:
- 谁打开这一页,在什么情境,要决定或理解什么?
- 最强的有据答案是什么?
- 哪些证据让答案可信?
- 哪个取舍、不确定性或限制会改变解读?
- 哪些要留著可查核,但不该主导第一眼?
正规化事实、单位、日期、来源、公式、矛盾、未知与隐私限制。区分观察、推导、推估、建议、因果。不替来源发明意图、负责人、急迫性、确定性、期限、核准或未来行为。
依读者需要排序,不依来源顺序。支援两种阅读速度:
- 决策路径:标题、小标、决定性数值、图说与结论,让人快速掌握论点。用最不专业的具名读者也能复述的白话写。
- 查核路径:精确表格、假设、方法、限制与来源,保留完整纪录。精确指标名、术语、单位与来源用语留在这里。
简化语言,不简化主张。保留每个会改变意义的限定条件、母体、期间、单位、比较基准与不确定性;「未限速」不等于「一般电脑」,「在量测误差内」不等于「一样快」。具体有据的陈述优于「很小、很大、安全、很快」这类评价性缩写。
每个章节回答一个新的读者问题;重复的合并,仪式性的删除。每个主张只有一个证据家:后面的表格可保留精确查询,但第二个摘要、图表、卡片组或结论不得以同等份量重述同一答案。
冗长帐册放在决策路径之后或原生折叠里。可筛选的大表预设显示中立且与决策相关的子集(全部失败、全部例外、决策点名的每一列),不是「全部」也不是挑选有利的列;标明目前筛选规则,保留查看全部的方法与目前/总计数量。
完成判据:上面五个问题都有一句话答案,且决策路径与查核路径的内容已分开。
2. 选择构图
第一屏就是论点,不是标题栏加铺陈。可以由主张、证据、比较或工具领头;若读者只看到第一屏,应记得核心关系、决定或工具,而不只是标题或气氛。
动手前先私下说出这类文件「理所当然」的版面,然后拒绝它,除非素材真的需要。素材允许多种结构时,私下比较两个拓扑、密度、证据位置都不同的构图假设,选让读者任务最清楚、中介最少的那个;只换配色或元件不算不同假设。
依任务决定开场:
- 明确建议或结论:答案与其决定性依据并列为主。
- 比较:把替代方案放在同一视觉基准上,差异用看的,不用从文字重建。
- 趋势或基准:让关系或例外领头,精确纪录放下面。
- 计算器或互动工具:操作假设是读者主要任务时,工具本身就是焦点证据,不先放一个静态证明。
- 没有有据结论的简报:以最强的有据状态、含义、限制或未决问题领头,不发明行动呼吁。
先选几何,再选元件。把素材对应到视觉变数:
| 素材 | 视觉变数 |
|---|---|
| 量级或排名 | 同一尺度上的位置或长度 |
| 随时间变化 | 水平顺序与对齐位置 |
| 组成 | 比例 |
| 门槛或区间 | 与边界的距离 |
| 流程或依赖 | 连线与顺序 |
| 定性替代方案 | 对齐的列或刻意对比的栏 |
表格用于精确查询,散文用於单一结论,图表只用在视觉化后更快理解的关系上。有数值不等于要画长条图。
把页面当成一个场,不是元件堆叠。全页一条主线,每个阅读时刻或主要区块一个焦点关系,焦点周围少量支援物件与足够留白。刻意安排卷动节奏:密度与安静交替,但只用一套视觉文法。重复只在项目是真正的同侪时才形成韵律,否则是模板噪音。结尾落在已解决的决定、含义、下一步或未决问题;来源与页尾安静地跟在后面,不让页面停在帐册或警语上。
每个产物要有一个属于这份素材的证据性组织手法(比较几何、门槛、序列、客制图解、独特的证据节奏或互动本身),不能原封不动搬到不相干的页面。它澄清主题,不装饰主题。
What ships with it
4 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 · 105 lines · 86 tokens per session scan A 3262884e0116
reader-led-design is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 2,211 once invoked, about $0.0003 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 2026-10-30.
reader-led-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reader-led-designhxy91819/mason-skills | Skill | 3 | today | MIT | A | 86 | Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |