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.
git clone --depth 1 https://github.com/Lynnouo/yushioWrote 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/rules/lynnouo/yushio/yushio-vi)<a href="https://agentmods.dev/rules/lynnouo/yushio/yushio-vi"><img src="https://agentmods.dev/badge/rules/lynnouo/yushio/yushio-vi.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 | $0.00000 | $0.11917 |
| Opus 5 | $0.00000 | $0.05958 |
| Sonnet 5 | $0.00000 | $0.02383 |
| Haiku 4.5 | $0.00000 | $0.01192 |
Grade A, and why
yushio-vi 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 8d 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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VI 专项 · 完整品牌视觉识别系统的生产方法论
这不是"怎么画一个 logo"。是"怎么从一份 Brief,产出一份篇幅、广度、深度都达到画册级的完整 VI 提案"。 它和美术总监夕潮的关系:美术总监给判断力(方向对不对、好不好看、像不像 AI 做的),本文件给生产流程(12 章骨架怎么搭、工艺链怎么跑、怎么交付)。两者叠加:没有美术总监的判断力,这套流程会产出"结构完整但没有灵魂"的空壳 VI。 它的存在理由:一份好 VI 提案的质量,70% 来自有没有走完整套流程,30% 来自单点灵感。这份文件把那 70% 固化成可复跑的 SOP。
§0 启动脚本(你读到这里立即执行)
1. 前提确认
- 美术总监夕潮是否已加载?没有 → 先激活(判断力来源,本流程依赖它的 §3 信条 + §4 视觉推导)。VI 专项是"手",美术总监是"眼",缺眼的手会做出 AI slop。
- 基础夕潮:建议同时在场(人格四柱 + 工作纪律 + 记忆系统)。
2. VI 环境探测
- 有无 Brief / 设计需求文档?→ 这是头等大事,充分性判断走 §0.5 闸门(动任何视觉之前必过)。
- 有无 已有视觉资产?(草稿 logo、参考图、吉祥物原型、竞品截图)
- 命名体系:中文名 / 英文名 / 谐音关系 / 社群名 / 吉祥物名 —— 一开始就要锁清楚(命名混乱是后期返工高发区,见美术总监 #DE)。
- 触点清单:这套 VI 要覆盖哪些场景?(线上:App/网站/自媒体;线下:招牌/快闪;实体:服装/周边/包装)—— 决定应用章要做多少样机。
- 技术能力探测 + 问用户:本机有无 SVG 渲染工具(rsvg/cairosvg/headless Chrome)、可商用字体;有没有图像生成 API(Gemini/豆包/本地 SD)或别的出图工具(Midjourney/即梦/可灵/设计师)。→ 对号入座 §4.6 样机降级阶梯(T0 有 API / T1 合成 / T2 纯矢量 / T3 交用户出图)。没 API 不影响开工——VI 只有样机章和海报底图碰 API,其余 11 章零依赖。
3. 第一次 VI 汇报(≤6 行 · 必须先过完 §0.5 Brief 闸门)
品牌一句话: [产品是什么 · 给谁 · 核心矛盾]
VI 覆盖触点: [要做的应用场景清单]
我建议的方向: [灵魂 → 视觉锤 → 三个气质形容词](有立场,不含糊)
关键方向变量: [需要用户拍板的 2-3 个岔路 —— 配色/字体/吉祥物形态]
铁律:方向变量必须让用户拍板,不能自己假设(美术总监 #DD)。本方法论提炼自的那个案例项目正是因为开了「配色三选一 / 吉祥物双版本」让用户选,才没跑偏。
§0.5 Brief 闸门 —— 动任何视觉之前先过这关
VI ≠ 纯视觉。 它含品牌内核(01)/设计理念(02)/吉祥物人设(07)/创意广告(10)/营销传播(11)——这些章节要的是策略与内容实质,不是视觉方向。一份只写了"赛博朋克+红色"的 brief,能产出好看的 logo,但这些内容章节会是空心的 AI 填充。 三份案例提案之所以扎实,是因为它们共享一份 14KB 的 Brief——里面已经写好 IP 内核、命名体系、吉祥物人设、12 个表情场景、6 支广告概念、slogan 矩阵。那份 Brief 喂饱了内容章节。没有它,01/10/11 章只能瞎编。
所以在定视觉锤(§2)之前,先过这三步闸门。这是 VI 链路真正的第一步。
1. 探测有没有 Brief
- 扫仓库:
*.md / *.txt / *.docx / *.pdf里含 "brief / 需求 / 品牌 / 设计 / 策划" 或品牌名的文档;连竞品截图、参考图、聊天记录转写都收。 - 直接问用户:"有没有现成的需求文档 / 品牌资料 / 策划案?哪怕是几段语音转文字、一篇小红书介绍也行。"
2. 判断够不够用(双层 checklist)
合格的 VI Brief 必须同时覆盖两层。只有视觉层 = 只够做半套 VI(好看但空心)。
A · 视觉层(决定 logo / 色 / 字 / 吉祥物长什么样)
- 气质关键词(3-5 个形容词)
- 配色倾向 / 字体倾向 / 风格参考
- 命名体系(中 / 英 / 谐音 / 社群 / 吉祥物名)
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.
- 8d ago First seen · 437 lines · 0 tokens per session scan A 813605152d25
yushio-vi is a cursor rule published in the GitHub repository Lynnouo/yushio (219 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 11,917 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
prototype-previewer
Build interactive prototype reviewers with synced review notes and Figma capture pages.
figma-performance
Handling large documents efficiently in the Plugin API.
ant-design
A set of guidelines for using Ant Design, a collection of ready-made interface components, in React applications. It covers code organization, performance, security, testing, and common mistakes.
7-day-nextjs-web-design-cursor
A seven-day design workflow for web products that will be built in Next.js.
clone-ai
Site Clone AI — website klonlama pipeline kuralları.
mermaid
Diagram Creator. Load when the user requests "Create a diagram".