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 caoxg/claude-skill-aesthetic-foundations --skill aesthetic-foundationsgit clone --depth 1 https://github.com/caoxg/claude-skill-aesthetic-foundationsWrote 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/caoxg/claude-skill-aesthetic-foundations/aesthetic-foundations)<a href="https://agentmods.dev/skills/caoxg/claude-skill-aesthetic-foundations/aesthetic-foundations"><img src="https://agentmods.dev/badge/skills/caoxg/claude-skill-aesthetic-foundations/aesthetic-foundations/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/caoxg/claude-skill-aesthetic-foundations/aesthetic-foundations"><img src="https://agentmods.dev/badge/skills/caoxg/claude-skill-aesthetic-foundations/aesthetic-foundations.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 | $0.00200 | $0.01030 |
| Opus 5 | $0.00100 | $0.00515 |
| Sonnet 5 | $0.00040 | $0.00206 |
| Haiku 4.5 | $0.00020 | $0.00103 |
Grade A, and why
aesthetic-foundations 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 12d 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.
What it actually says
Aesthetic Foundations
这个 skill 在你接到视觉判断任务时, 先把审美词汇激活, 然后再开始评审或建议. 没有它的话默认会滑回"通用 web 风格": 圆角、Material 阴影、彩虹色 badge — 那不是审美, 那是肌肉记忆.
触发后第一件事
别立刻给答案. 先做一次 critique-protocol 7 步走:
- 三秒第一印象 — 眼睛先落在哪?
- 眯眼测试 — 层次还在吗?
- 灰度测试 — 转黑白还能不能用?
- 留白测试 — 空白是"意味" 还是"没填满"?
- 裁剪测试 — 能砍掉什么?
- 大师参照 — 哪条原则被违反 / 被尊重?
- 改动清单 — 3-5 个具体动作, 不要"再干净一点"
加载哪些 reference (按主题)
| 任务 | 必看 |
|---|---|
| 布局 / 构图 | references/composition.md + references/grid-and-rhythm.md |
| 色彩 | references/color.md |
| 字体 / 排印 | references/typography.md |
| 信息层级 | references/visual-hierarchy.md |
| 空 / 留白 | references/ma-and-negative-space.md |
加载哪些 master (按情境)
| 情境 | 看谁 |
|---|---|
| 光与窗 / 单光源场景 | Vermeer (painters.md) |
| 平衡 + 非对称 | Mondrian, Bada Shanren (painters.md / 中式审美.md) |
| 用色块情绪 | Rothko (painters.md) |
| 决定性瞬间 / 几何瞬间 | 布列松 (photographers.md) |
| 隔离主体 / 极简肖像 | Avedon (photographers.md) |
| 工业克制 / 功能美 | Dieter Rams (designers.md) |
| 网格 + 极少字体 | Vignelli (designers.md) |
| 留白 / 东方极简 | 原研哉 + 中式审美.md |
| 中式语境 / 项目用中文 | masters/中式审美.md 优先于 Bauhaus |
不变量 (别忘了)
- 审美不是规则集 — 是张力. 三分法 vs 居中, 网格 vs 破格, 都对, 看情境.
- 先看后说 — 任何"建议"前必须先描述眼睛实际看到的 (眼动 / 焦点 / 层次), 不要直接跳到 "建议把 padding 加到 16px".
- 不要逃进 hex — "把 ink3 改成 ink2" 是 token 操作, 不是设计判断. 判断是: "这里需要更弱的灰让标题更突出".
- 数量级而非数值 — "留白翻倍" 比 "padding 24→48" 更靠近设计语言. 像素是结果, 不是输入.
- 不与 frontend-design 抢活 — 那个 skill 管"web UI 是否符合工程规范". 这个 skill 管"为什么这样组合好看".
What ships with it
11 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.
- critique-protocol.md 5.2 KB
- masters/designers.md 7.6 KB
- masters/painters.md 7.2 KB
- masters/photographers.md 6.3 KB
- masters/中式审美.md 8.5 KB
- references/color.md 6.7 KB
- references/composition.md 5.8 KB
- references/grid-and-rhythm.md 5.5 KB
- references/ma-and-negative-space.md 6.0 KB
- references/typography.md 6.9 KB
- references/visual-hierarchy.md 6.1 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.
- 12d ago First seen · 66 lines · 200 tokens per session scan A 278a07b9094e
aesthetic-foundations is a skill published in the GitHub repository caoxg/claude-skill-aesthetic-foundations (9 stars, last pushed 4mo ago), licensed MIT. It adds 200 tokens to every session and 1,030 once invoked, about $0.0010 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
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
pixel2motion
Turn a raster logo (PNG/JPG/WebP/screenshot) into a clean minimal SVG with edge smoothness as the primary hard gate and IoU optimized as high as reasonably possible without a fixed global threshold, then into a choreographed logo animation delivered as standalone JS-rendered HTML, applying Disney's 12 animation…
superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…
higgsfield-moodboard
Use when the user asks about Moodboard, building a moodboard from reference images, curated moodboard presets, Soul Hex color transfer, applying a visual style direction to generations, or named moodboard styles like Y2K studio, Warm ambient, Theatrical light, Swag era, Flash editorial, Street photography, Asian…
design-stylecards
Declarative catalog of named aesthetic recipes — exact shadow stacks, glass surfaces, gradient treatments, and type scales as copy-paste values with Use-When and Avoid rules. Use when the user asks for polished elevation, glassmorphism, a border gradient, a mesh background, or any 'make it look like X' request where…
image-to-svg
Convert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use when the user uploads an image and asks to reproduce, vectorize, trace, or convert it to SVG. Also use when asked to decompose an image into shapes, create an SVG version of a picture, or faithfully reproduce artwork…