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 commands/kimyx0207/claudecode-codex-gemini/kim-ui2codegit clone --depth 1 https://github.com/KimYx0207/Claudecode-Codex-GeminiWrote 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/commands/kimyx0207/claudecode-codex-gemini/kim-ui2code)<a href="https://agentmods.dev/commands/kimyx0207/claudecode-codex-gemini/kim-ui2code"><img src="https://agentmods.dev/badge/commands/kimyx0207/claudecode-codex-gemini/kim-ui2code.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 | $0.00025 | $0.02988 |
| Opus 5 | $0.00013 | $0.01494 |
| Sonnet 5 | $0.00005 | $0.00598 |
| Haiku 4.5 | $0.00003 | $0.00299 |
Grade A, and why
kim-ui2code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kim截图转代码命令(四阶段三引擎)
公众号:老金带你玩AI | 微信:xun900207 | 备注AI加入AI交流群
你现在要协调3个AI工具,将UI设计稿/截图转换为可运行的前端代码:$ARGUMENTS
核心流程:Gemini(看图) → Claude(分析) → Codex(生成) → Gemini(审查)
⚠️ 文件写入规则(必须遵守)
Claude Code的Write工具要求:写入文件前必须先读取它。对于新文件:
# 创建新文件的标准流程:
1. 用 Bash 创建目录和空文件:mkdir -p 目录 && echo "" > 文件路径
2. 用 Read 读取该文件
3. 用 Write 写入实际内容
执行流程
阶段0.1:健康检查
参考 .claude/skills/kim-orchestrator/prompts/health-check.md 执行MCP健康检查。
本命令必须同时使用Gemini和Codex:
- 检测
mcp__gemini__gemini(图像识别必需) - 检测
mcp__codex__codex(代码生成必需)
根据检测结果:
- ✅ 全部可用 → 继续执行完整流程
- ❌ Gemini不可用 → 无法执行(核心能力缺失,无法看图)
- ⚠️ Codex不可用 → 询问是否用Claude降级生成(质量可能下降)
阶段0.2:初始化工作目录
mkdir -p .kim-orchestrator/ui2code && echo "" > .kim-orchestrator/ui2code/phase1_vision.json && echo "" > .kim-orchestrator/ui2code/phase2_spec.json && echo "" > .kim-orchestrator/ui2code/phase3_code.md && echo "" > .kim-orchestrator/ui2code/phase4_review.md && echo "" > .kim-orchestrator/ui2code/result.md
然后读取这些文件:
- Read .kim-orchestrator/ui2code/phase1_vision.json
- Read .kim-orchestrator/ui2code/phase2_spec.json
- Read .kim-orchestrator/ui2code/phase3_code.md
- Read .kim-orchestrator/ui2code/phase4_review.md
- Read .kim-orchestrator/ui2code/result.md
阶段0.3:获取截图
根据用户输入类型处理:
情况1:本地文件路径
如果 $ARGUMENTS 是本地文件路径(如 ./design.png, C:\screenshots\ui.jpg)
→ 使用 Read 工具读取图片文件
→ 将图片内容传递给Gemini
情况2:URL链接
如果 $ARGUMENTS 是URL(如 https://example.com/design.png)
→ 直接将URL传递给Gemini
情况3:用户未提供
→ 询问用户提供截图路径或URL
→ 或者让用户直接粘贴图片到对话中
阶段1:视觉分析(Gemini)
调用 mcp__gemini__gemini 分析截图:
Prompt模板:
请仔细分析这张UI设计截图,提取以下信息:
## 1. 整体布局
- 页面类型(登录页/列表页/详情页/表单页/Dashboard等)
- 整体布局结构(顶部导航+侧边栏+主内容区等)
- 响应式设计要求(移动端/PC端/自适应)
## 2. 组件清单
列出所有可识别的UI组件:
- 按钮(样式、状态、位置)
- 输入框(类型、placeholder、验证)
- 卡片/列表项
- 导航栏/菜单
- 图标/图片
- 表格/数据展示
- 弹窗/模态框
- 其他组件
## 3. 样式信息
- 主色调和配色方案
- 字体大小层级
- 间距规律
- 圆角/阴影等视觉效果
## 4. 交互暗示
- 可点击元素
- 悬停效果暗示
- 表单验证提示
- 状态切换
请以结构化JSON格式输出分析结果。
将Gemini的响应保存到 .kim-orchestrator/ui2code/phase1_vision.json
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.
- 4d ago First seen · 395 lines · 25 tokens per session scan A 492350469d23
kim-ui2code is a command published in the GitHub repository KimYx0207/Claudecode-Codex-Gemini (119 stars, last pushed 22d ago), licensed MIT. It adds 25 tokens to every session and 2,988 once invoked, about $0.0001 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 commands, from other repositories
motion-design
Design micro-interactions, transitions, and animation systems for UI components or full pages.
ux-motion
Animation and motion rubric. Checks timing, easing, meaning, reduced-motion compliance, and performance for every animation on a surface. Triggers on "motion check", "are the animations good", or "fix the motion". Use when auditing motion or animations, checking durations / easing / reduced-motion / performance, is…
ux-recommend
The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
designer
DaisyUI로 예쁜 UI를 만들거나, 기존 UI를 바꿔줘요.