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 rules/lxxgg92/xianxin-design-workflow/cursorgit clone --depth 1 https://github.com/lxxgg92/xianxin-design-workflowWrote 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/lxxgg92/xianxin-design-workflow/cursor)<a href="https://agentmods.dev/rules/lxxgg92/xianxin-design-workflow/cursor"><img src="https://agentmods.dev/badge/rules/lxxgg92/xianxin-design-workflow/cursor.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 | $0.00046 | $0.02100 |
| Opus 5 | $0.00023 | $0.01050 |
| Sonnet 5 | $0.00009 | $0.00420 |
| Haiku 4.5 | $0.00005 | $0.00210 |
Grade A, and why
cursor 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 6d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design
用于新项目初始化或更新已有项目的设计规范。当用户提供 Figma 链接、参考图或设计稿，且任务涉及新项目初始化、页面交付或设计规范落地时执行此 skill。负责项目级设计规则；单页面结构拆解应进入 spec。不适用于临时修改、小 bug 修复、零碎问题等非交付类任务。
前置判断
触发后按以下顺序判断当前状态，再决定执行路径：
第一步：确认项目路径
- 如果上下文中没有明确项目路径，先向用户确认
第二步：检查项目内文件分层
- 基础文件：
- DESIGN.md
- UI_SPEC.md 或 UI_SPEC_*.md
- Handoff.md
- 最终交付产物：
- delivery-report.md
第三步：根据检查结果分流
-
新项目（基础文件均不存在）：
- 检查用户是否已提供足够信息，缺少时一次性整理所有缺失项后统一反馈，不逐条追问
- 新建 DESIGN.md 时至少需要确认：产品类型、目标用户、品牌气质、主色、是否有参考图或 Figma 链接、端类型（B 端 / C 端 / 移动端 / Web 等）、是否有已有组件库或 UI 框架
- 信息齐全后生成 DESIGN.md，再引导进入 → spec
-
更新项目（DESIGN.md 已存在）：
- 先读取现有 DESIGN.md，不覆盖原有规则
- 检查是否存在 UI_SPEC.md（或命名为 UI_SPEC_*.md 的任何页面规格文件）、Handoff.md
- 如果缺少其中任意基础文件：一次性告知用户缺了哪些、各文件用于什么阶段、是否需要重新生成
- 如果缺少 delivery-report.md：仅说明项目尚未进入最终交付阶段，不视为异常
- 如果 DESIGN.md 与本轮需求冲突：先指出冲突，再给出建议，不直接覆盖
-
部分文件缺失（有些存在有些不存在）：
- 一次性列出所有缺失文件，说明各文件用途，询问是补全还是重新开始
输入
新建 DESIGN.md 时：
- 品牌信息（品牌色、气质、关键词）
- 页面参考图、原型或 Figma 链接
- 产品类型、端类型（Web / 移动 / PC 等）
- 已有组件库信息（如有）
更新已有 DESIGN.md 时：
- 现有 DESIGN.md 文件
- 变更需求说明（新增 token、修改规则、扩展组件等）
- 当前项目路径下已有的 UI_SPEC.md / Handoff.md / delivery-report.md（如有）
输出
- DESIGN.md 文件（YAML 前置数据 + Markdown 正文）
- 对用户的阶段性说明：
- 当前判断是新项目还是更新项目
- 当前缺少哪些文件或信息
- 下一步应进入哪个 skill（通常是 → spec）
暂停点
- DESIGN.md 生成或更新完成后，必须暂停，告诉用户：
- 当前设计规范是否已建立完成
- 是否还有缺失文件需要补齐
- 下一步建议进入 → spec
- 不要在用户确认前自动继续执行下一个步骤
DESIGN.md 格式规范
DESIGN.md 由两层组成：
- YAML 前置数据（
---包裹）：机器可读的 design token，包含精确数值 - Markdown 正文：人类可读的设计理由，说明 token 背后的逻辑
YAML Schema
version: alpha # 可选
name: <项目名>
description: <项目描述> # 可选
colors:
<token-name>: "#hex"
typography:
<token-name>:
fontFamily: <string>
fontSize: <px/rem>
fontWeight: <number>
lineHeight: <px/rem/number>
letterSpacing: <Dimension> # 可选
fontFeature: <string> # 可选，对应 font-feature-settings
fontVariation: <string> # 可选，对应 font-variation-settings
rounded:
<scale>: <px/rem>
spacing:
<scale>: <px/rem>
components:
<component-name>:
backgroundColor: <Color 或 {token.path}>
textColor: <Color 或 {token.path}>
typography: <{token.path}>
rounded: <{token.path}>
padding: <Dimension>
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.
- 6d ago First seen · 182 lines · 46 tokens per session scan A a9db298197d3
cursor is a cursor rule published in the GitHub repository lxxgg92/xianxin-design-workflow (35 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 2,100 once invoked, about $0.0002 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 2026-08-30.
Other cursor rules, from other repositories
frontend
Demo Shop frontend guidance.
steward
Global Steward Governance.
token-the-ripper
Strip scaffolding. Keep signal.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.