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 YiShu5/claude-skills --skill fangpian-brand-kitgit clone --depth 1 https://github.com/YiShu5/claude-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/yishu5/claude-skills/fangpian-brand-kit)<a href="https://agentmods.dev/skills/yishu5/claude-skills/fangpian-brand-kit"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/fangpian-brand-kit/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/yishu5/claude-skills/fangpian-brand-kit"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/fangpian-brand-kit.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 | $0.00173 | $0.01782 |
| Opus 5.5 | $0.00069 | $0.00713 |
| Sonnet 5.5 | $0.00035 | $0.00356 |
| Haiku 4.5 | $0.00017 | $0.00178 |
Grade A, and why
fangpian-brand-kit 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 yesterday.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
方片品牌形象库（FANG PIAN Brand Kit）
本技能是方片新媒体的品牌视觉单一事实来源。做任何视觉物料前，先加载本规范，再从 assets/ 直接取用现成素材，禁止凭空重画 logo、重配颜色、替换字体或乱换 IP。
资产目录
assets/logos/— 透明底「方片」字标（黑/黄/白三色）与母品牌、赛道子品牌标准组合（lockup）assets/colors/— 黄 / 黑 / 银官方背景色卡（取色、对色用）assets/ip/— 方片老虎 IP 透明底素材，按场景命名（01–20）assets/fonts/— 中英文标准字体预览（字体安装文件需向设计部门索取，见 references）
硬性品牌规范（不可违反）
- Logo 用官方文件，不许重绘：字标是书法手写体「方片」+ 下方字距拉开的
FANG PIAN。只能从assets/logos/取透明 PNG，按背景选颜色：- 浅色/白/黄底 →
logo-fangpian-black.png（黑字） - 黑底/深色底 →
logo-fangpian-white.png（白字）或logo-fangpian-yellow.png（黄字） - 黄底用黑字。禁止拉伸、压扁、加阴影、描边、旋转、改字、换书法字体。
- 四周留足不小于「片」字笔画高度的安全区，安全区内不压文字、不放别的图形。
- 浅色/白/黄底 →
- 配色只用官方色板：
- 主色 方片黄
#FFF300（RGB 255/243/0，CMYK 8/1/86/0） - 黑
#000000、金属银（银色渐变，取色见assets/colors/bg-silver.png，约#D1D1D1一带） - 子品牌紫
#8A66FA（RGB 138/102/250）用于方片时尚、方片家居 - 经典高对比组合是「黑 + 黄」「黑底黄字」；黄色是大面积品牌色，不要把它降成暗黄或橙黄。
- 主色 方片黄
- 字体只用授权的四款，不要用系统默认黑体或免费字体替代：
misan（黑体，10 字重）——正文/常规信息主力pop（黑体，16 字重，含斜体）——强调、大标题江城圆体（圆幼，6 字重）——亲和、活泼、母婴/生日/员工向字体圈欣意冠黑体（艺术体）——数字、主标题、视觉焦点- 英文/数字走
DIAMOND NEWMEDIA一套字重（见assets/fonts/preview-en.png）。品牌 Slogan：「快速创新 无限成长」。
- IP 老虎用现成透明图，按场景选姿势：3D 黄色小老虎是方片 IP，不要自己重画或改色。从
assets/ip/选与语义匹配的姿势（选图对照见 references/brand-identity.md）。IP 同样留安全区，不被裁切到脸、尾巴、手持物。 - 子品牌用对应 lockup：母婴用
lockup-muying.png（黄底黑字）、时尚用lockup-shishang.png（紫底白字）、家居用lockup-jiaju.png（白底紫字）、集团口径用lockup-xinmeiti.png。给某赛道做物料，必须用该赛道 lockup，不要混用。
做物料的标准流程
- 定类型：对照 references/poster-templates.md 找到最接近的部门模板与画布比例（入职/周年/生日/培训会/线上课/博主签约/股东积分/大事件水印/灯箱）。有现成
.ai模板就「换字、换色、换素材」，不要另起炉灶。 - 定主体：是集团还是某赛道（母婴/时尚/家居），决定用哪套 logo 和配色。
- 摆 logo：放在固定角位（多为左上或右上），给安全区，按背景选字标颜色。
- 选 IP 姿势：按场景语义选
assets/ip/对应图（如培训会用04-teacher，签约用08-money或12-ok，生日会用07-boba-cake，短视频用18-clapperboard）。 - 排字：用四款授权字体，建立「主标题（艺术/pop）→ 副标题（misan）→ 时间地点等信息（misan）」层级；正文不用书法字。
- 收尾检查：颜色取色与色卡一致；logo/IP 没变形、没被裁；安全区干净；无错别字；导出 PNG（屏幕用）或按模板交付。
What ships with it
34 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.
- assets/colors/bg-black-and-silver.png 12 KB
- assets/colors/bg-silver.png 40 KB
- assets/colors/bg-yellow.png 14 KB
- assets/fonts/preview-cn.png 275 KB
- assets/fonts/preview-en.png 98 KB
- assets/ip/01-hero-cool.png 1207 KB
- assets/ip/02-welcome-peace.png 1313 KB
- assets/ip/03-reading-book.png 1068 KB
- assets/ip/04-teacher.png 1306 KB
- assets/ip/05-pets-cat-dog.png 1488 KB
- assets/ip/06-eating-chopsticks.png 1310 KB
- assets/ip/07-boba-cake.png 1500 KB
- assets/ip/08-money.png 1008 KB
- assets/ip/09-trophy.png 1233 KB
- assets/ip/10-tennis.png 1271 KB
- assets/ip/11-lounging.png 1130 KB
- assets/ip/12-ok.png 1334 KB
- assets/ip/13-running.png 1583 KB
- assets/ip/14-police.png 1060 KB
- assets/ip/15-pointing.png 1233 KB
- assets/ip/16-ai-tech.png 2312 KB
- assets/ip/17-suit-business.png 2714 KB
- assets/ip/18-clapperboard.png 2065 KB
- assets/ip/19-clipboard-radio.png 1900 KB
- assets/ip/20-popcorn-3d.png 1513 KB
- assets/logos/lockup-jiaju.png 387 KB
- assets/logos/lockup-muying.png 437 KB
- assets/logos/lockup-shishang.png 416 KB
- assets/logos/lockup-xinmeiti.png 465 KB
- assets/logos/logo-fangpian-black.png 191 KB
- assets/logos/logo-fangpian-white.png 139 KB
- assets/logos/logo-fangpian-yellow.png 237 KB
- references/brand-identity.md 6.2 KB
- references/poster-templates.md 4.6 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.
- yesterday First seen · 65 lines · 173 tokens per session scan A 58edc2bb4432
fangpian-brand-kit is a skill published in the GitHub repository YiShu5/claude-skills (132 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 1,782 once invoked, about $0.0007 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 2026-10-17.
Other skills, from other repositories
hps-true-blueprint
OpenDesign's engineering blueprint: how the sandbox, sidecar, and daemon fit — the system diagram and the invariants. Built as a decision-grade product management deck for engineering org.
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
3d-web-experience
Use when building or debugging web 3D scenes, product configurators or portfolios with Three.js, React Three Fiber or Spline; review assets, loading, controls, fallbacks and performance.
agent-reels
Find animation and video references on 1human, consult a human-agent shared library, and contribute public creations only with prior owner permission.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
anti-ui-slop
Stop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.