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/bybren-llc/rendertrust/sketch-to-codegit clone --depth 1 https://github.com/bybren-llc/rendertrustWrote 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/bybren-llc/rendertrust/sketch-to-code)<a href="https://agentmods.dev/commands/bybren-llc/rendertrust/sketch-to-code"><img src="https://agentmods.dev/badge/commands/bybren-llc/rendertrust/sketch-to-code.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 | $0.00000 | $0.00748 |
| Opus 5 | $0.00000 | $0.00374 |
| Sonnet 5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
sketch-to-code 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 today.
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.
This is a copy
100% identical to sketch-to-code — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description = "Generate code from UI sketches, wireframes, or mockups"
prompt = """
Sketch to Code Command
Transform hand-drawn sketches, wireframes, or UI mockups into functional code using Gemini's multimodal vision.
Input: {{args}}
Supported Input Types
- Hand-drawn sketches (paper, whiteboard photos)
- Digital wireframes
- UI mockups (Figma screenshots, etc.)
- Flowcharts and diagrams
- Architecture diagrams
Workflow
1. Analyze the Visual Input
Read and understand the sketch/mockup:
!{ls -la {{args}} 2>/dev/null || echo "File not found"}
Identify:
- UI components (buttons, inputs, cards, navigation)
- Layout structure (grid, flex, sections)
- Visual hierarchy
- Interactive elements
- Data flow (if flowchart)
2. Determine Output Framework
Ask user or detect from project context:
- React (with hooks, TypeScript optional)
- Next.js (App Router)
- Vue (Composition API)
- HTML/CSS (vanilla)
- Tailwind CSS (styling)
- shadcn/ui (component library)
Check project for existing framework:
!{cat package.json 2>/dev/null | grep -E '"react"|"next"|"vue"' | head -3 || echo "No package.json found"}
3. Generate Code
Based on sketch analysis, generate:
Component Structure:
ComponentName/
├── index.tsx # Main component
├── styles.css # Styles (if not Tailwind)
└── types.ts # TypeScript interfaces
Code Output:
- Semantic HTML structure
- Responsive layout (mobile-first)
- Accessibility attributes (ARIA)
- Placeholder content matching sketch
- Interactive states (hover, focus, active)
4. Output Location
Save generated code to appropriate location:
!{ls -d src/components 2>/dev/null || ls -d components 2>/dev/null || echo "./"}
Usage Examples
# From hand-drawn sketch
/media:sketch-to-code ./whiteboard-photo.jpg
# From Figma screenshot
/media:sketch-to-code ~/Downloads/figma-export.png
# From wireframe with framework hint
/media:sketch-to-code ./wireframe.png --react --tailwind
# From architecture diagram
/media:sketch-to-code ./system-diagram.png --mermaid
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.
- today First seen · 119 lines · 0 tokens per session scan A 96f82602d770
sketch-to-code is a command published in the GitHub repository bybren-llc/rendertrust (7 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 748 tokens. A static security scan graded it A with 0 findings. It is 100% identical to sketch-to-code, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
kim-form
Kim表单生成命令 - 根据字段描述生成React/Vue表单组件(含校验逻辑).
scaffold-desktop
Scaffold a desktop application using Electron or Tauri with proper project structure.
media-sketch-to-code
Gemini-only command that turns sketches, wireframes and mockups into framework-specific component code or Mermaid diagrams.
component-gen
Generate React or Vue components with prop types, styling, accessibility, and tests.
dare-frontend-design
Arquitetura frontend DARE para projetos React e Vue. Detecta god components, fetch inline em JSX/template, e gera scaffold DARE-compliant.
frontend
Show me recent frontend development articles (React, Vue, performance, UX, build tools).