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 Jerrylalala/compound-engineering --skill ui-review-contractgit clone --depth 1 https://github.com/Jerrylalala/compound-engineeringWrote 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/jerrylalala/compound-engineering/ui-review-contract)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/ui-review-contract"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/ui-review-contract/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/jerrylalala/compound-engineering/ui-review-contract"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/ui-review-contract.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 | $0.00068 | $0.01509 |
| Opus 5 | $0.00034 | $0.00754 |
| Sonnet 5 | $0.00014 | $0.00302 |
| Haiku 4.5 | $0.00007 | $0.00151 |
Grade A, and why
ui-review-contract 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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Review Contract — 四信号门触发协议
背景（Codex P9 → P4 提前）：
ce:work已有 Figma Design Sync 步骤，但缺乏统一的触发协议。 本 overlay 收敛现有 UI 检测行为为可预期的四信号门规则。
四信号门定义
| 信号 | 类型 | 检测内容 |
|---|---|---|
| Plan Signal | 计划/需求 | 出现 UI 相关词：component、page、screen、layout、style、design、responsive、visual、UI、UX、界面、页面、样式、组件 |
| File Signal | 改动文件 | 匹配：*.css、*.scss、*.tsx、*.jsx、*.vue、*.html、components/、pages/、views/、styles/、design-tokens/ |
| Artifact Signal | 工件引用 | 出现：Figma URL、screenshot、visual diff、design spec、mockup |
| Exclusion Signal | 排除条件 | 匹配：API design、database design、schema、纯 CLI/后端任务（无 File Signal 匹配时排除） |
触发规则
满足以下任意一组组合才触发 Design Review（单个信号不触发）：
| 组合 | 说明 |
|---|---|
Plan + File |
计划提到 UI + 有前端文件改动 |
File + Artifact |
有前端文件改动 + 有设计工件引用 |
Plan + Artifact |
计划提到 UI + 有设计工件 |
Exclusion Signal 覆盖：如果 Exclusion Signal 触发且 File Signal 未触发，不做 Design Review。
触发后行为
当四信号门判断需要 Design Review 时，在 ce:review 的 Advisory Tier 中增加 UI 审查：
1. 加载设计审查代理（并行）
design-implementation-reviewer — 视觉对齐检查（如有 Figma URL）
figma-design-sync — Figma 设计同步检查（如有 Figma URL）
design-iterator — 迭代改进建议（N 轮截图-分析-改进循环）
2. 设计审查输出格式
使用 Review Contract 的 Advisory Tier 规则（autofix_class: advisory），额外字段：
# 设计 finding 额外字段
design_check:
figma_url: "https://figma.com/..." # 如有
screenshot: "path/to/screenshot.png" # 如有
visual_diff: "描述视觉差异"
severity: P2 | P3 # 设计问题最高 P2（不 blocking）
3. 输出 Checklist
设计审查完成后生成 checklist（插入 review.md）：
## UI Review Checklist
- [ ] 组件间距符合设计规范
- [ ] 颜色/字体与 design token 一致
- [ ] 响应式布局在移动端正常
- [ ] 无障碍性（aria labels、contrast ratio）
- [ ] 加载/空/错误状态已实现
与现有工作流集成
ce:work 中的集成点
在 ce:work Phase 3 质量检查阶段，已有 Figma Design Sync 步骤：
# 原有步骤（保留）
6. Figma Design Sync (if applicable)
# 本 overlay 增加
6.5 四信号门检查：是否需要 Design Review？
└─ 是 → 加载 design-implementation-reviewer
└─ 否 → 跳过
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.
- 9d ago First seen · 138 lines · 68 tokens per session scan A cd41fc28715e
ui-review-contract is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 1,509 once invoked, about $0.0003 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.