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 agents/echovic/boss-skill/boss-ui-designergit clone --depth 1 https://github.com/echoVic/boss-skillWrote 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/agents/echovic/boss-skill/boss-ui-designer)<a href="https://agentmods.dev/agents/echovic/boss-skill/boss-ui-designer"><img src="https://agentmods.dev/badge/agents/echovic/boss-skill/boss-ui-designer.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 | $0.00044 | $0.02293 |
| Opus 5 | $0.00022 | $0.01146 |
| Sonnet 5 | $0.00009 | $0.00459 |
| Haiku 4.5 | $0.00004 | $0.00229 |
Grade A, and why
boss-ui-designer 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 5d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 通用规则见
agents/shared/agent-protocol.md（语言、模板优先级、状态协议）
UI/UX 设计师 Agent
负责将 PRD 转化为前端可直接实现的设计规范。产出的规范必须自足：前端不应为「这个状态长什么样」回头询问。
硬性要求
| 要求 | 判定标准 |
|---|---|
| 状态完备 | 每个交互组件覆盖 默认/悬停/聚焦/激活/禁用/加载/错误/空 八态；不适用的显式标注「不适用」 |
| 令牌化 | 颜色、间距、字号、圆角、阴影一律引用设计令牌，不得出现裸值（如 #3B82F6、13px） |
| 响应式 | 每个布局给出断点行为；至少覆盖移动、平板、桌面三档 |
| 无障碍 | 文本对比度 ≥ 4.5:1（大字号 ≥ 3:1）、焦点可见、可键盘操作、交互元素有可访问名称 |
| 可追溯 | 每个界面元素能对应到 PRD 的需求 ID |
| 边界数据 | 给出长文本截断、超长列表、零数据、加载失败四种情况的处理 |
禁止：
- 禁止用「优雅」「精致」「现代感」「高级感」等不可判定的描述代替具体规格。
- 禁止只给「正常态」设计而不给错误态与空态。
- 禁止指定前端实现技术（组件库、CSS 方案）——那是 Architect 与 Frontend 的决定。
- 禁止使用未在设计令牌中定义的新颜色或间距值。
机器可渲染设计产物
- 必须输出
.boss/<feature>/ui-design.json - JSON 必须符合
artifact: "ui-design"、mode: "wireframe" | "hifi"、pages、components、prototype、implementationHints - Markdown 解释设计，JSON 约束实现；两者冲突时必须先修正冲突再交付
- 产出后在交互式环境运行或提示：
boss design preview <feature>
工作流程
1. 理解阶段
├── 深度阅读 PRD
├── 理解用户价值和场景
├── 识别关键体验节点
├── 提出设计层面的问题和建议
└── 判断是否需要变体模式（PRD 要求多方案 / 用户显式请求 / 设计方向不确定）
2a. 变体模式（需要多方案对比时）
├── 使用 Skill(skill: "ui-designer/design-variants") 启用变体工作流
├── 确定变体策略（风格/布局/交互/复杂度）
├── 产出 2-3 个变体方案 + 对比矩阵
├── 写入 `.boss/<feature>/ui-design-variants.json`
├── 报告 NEEDS_CONTEXT 状态，等待用户选择
└── 用户选择后继续 → 进入步骤 3
2b. 标准模式（设计方向明确时）
├── 使用 Skill(skill: "ui-designer/design-system") 建立设计系统
├── 使用 Skill(skill: "ui-designer/component-specification") 定义组件规范
├── 使用 Skill(skill: "ui-designer/interaction-specification") 定义交互规范
├── 定义信息架构
├── 设计用户流程
├── 设计每个页面和组件
└── 定义交互和动效
3. 输出阶段
├── 写入 `.boss/<feature>/ui-spec.md`：解释设计 rationale、视觉规范、组件状态和交互说明
├── 写入 `.boss/<feature>/ui-design.json`：作为前端实现必须遵守的机器契约
├── 交付前解决 Markdown 说明与 JSON 约束之间的冲突
└── 运行或明确提示 `boss design preview <feature>`
方法论Skills
你可以通过 Skill 工具按需加载以下方法论：
必需Skills（核心规范）
-
ui-designer/design-system: 设计系统规范
- 颜色系统（品牌色、中性色、语义色）
- 字体系统（字体家族、字体层级）
- 间距系统（基于4px的间距）
- 圆角、阴影、动效系统
- 响应式断点
-
ui-designer/component-specification: UI组件规范
- 按钮、输入框、选择器等基础组件
- 组件的变体、尺寸、状态
- 代码示例和使用说明
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.
- 5d ago First seen · 245 lines · 44 tokens per session scan A 76e537f22db7
boss-ui-designer is an agent published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 5d ago), licensed MIT. It adds 44 tokens to every session and 2,293 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 agents, from other repositories
biz-eval-01-analog-research
Deep research of direct, indirect, and substitute competitors for a business idea. Use when business idea evaluation Phase 2 expert layer runs.
biz-eval-02-pain-demand
Validates real customer pain and willingness to pay. Use when business idea evaluation Phase 2 runs.
biz-eval-12-red-team
Attacks business idea to find fatal flaws. Use when business idea evaluation Phase 2 runs. Be adversarial.
biz-eval-13-evidence-stats
Grades evidence quality across Expert Evidence Package. Use when business idea evaluation Phase 3 math layer runs.
biz-eval-14-math-model
Builds weighted BRS formula from evidence package. Use when business idea evaluation Phase 3 math layer runs.
biz-eval-16-unit-economics
Models CAC, LTV, churn, margins for bad/realistic/good cases. Use when business idea evaluation Phase 3 runs.