No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by ReScienceLab · Agent Tool · ★ 76
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is super-prototyping safe to install? View the security audit →
super-prototyping An agent plugin for rebuilding and designing product UI as self-contained HTML artboards on a local tldraw canvas, with the measuring toolkit and the agent skills that drive the work. Install it into any project; your boards stay in your project and the plugin upgrades around them. The point of it is a replica you can defend. Every colour and every metric on a cloned board traces back to a measurement of the source capture, and the capture itself is parked on the canvas directly under the replica, so the two are one glance apart rather than one memory apart. How you use it: install the plugin, start the canvas, then hand Claude Code your screenshots and ask for the skill. It grids the capture, samples it region by region, writes one measured token block, generates every board from a single , then re-renders those boards and diffs them against the capture until the numbers hold. does the same for screens that have no reference to measure. Both write files into , and the canvas picks them up as shapes with no registry, no build step and no design tool. Five worked examples Five of the fourteen app folders in . That folder's own lists them all.
| Stars | 76 |
| Forks | 3 |
| Language | HTML |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 67.4269911103542/100 |
| Open Issues | 15 |
| Last Updated | 2026-09-19 |
| Created | 2026-08-29 |
| Platforms | claude-code |
| Est. Tokens | ~21k |
These tools work well together with super-prototyping for enhanced workflows:
Looking for a super-prototyping alternative? If you're comparing super-prototyping with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Whiteboard tldraw diagrams (.tldr) from natural language with 6 presets and vision-based self-check. PNG/SVG e
Odoo MCP for AI agents — 41 tools, gated writes, multi-instance. Free hosted: ERPipe → mcp.erpipe.com
A virtual design team for Claude Code, Cursor, Windsurf, Gemini CLI, and Copilot — 26 roles, 62 commands, 15,0
Consulting firm-style PowerPoint design system for AI agents. 70 layout patterns, flat design, python-pptx. 麦麸
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
A virtual design studio for Claude Code — 27 slash commands, 13 specialist roles, full design-to-code pipeline
Explore other popular agent tool tools:
super-prototyping is Copy any app's UI, prototype your own — as plain HTML artboards on a local canvas. No design tool, no build step. Every color and metric traced to a measurement.. It is categorized as a Agent Tool with 76 GitHub stars.
super-prototyping is primarily written in HTML. It covers topics such as agent-skills, claude-code, design-system.
You can find installation instructions and usage details in the super-prototyping GitHub repository at github.com/ReScienceLab/super-prototyping. The project has 76 stars and 3 forks, indicating an active community.
super-prototyping is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to super-prototyping on Agent Skills Hub include tldraw-skill, mcp-odoo, naksha-studio. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: