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.
git clone --depth 1 https://github.com/BOXELS/cursor-rulesWrote 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/rules/boxels/cursor-rules/design)<a href="https://agentmods.dev/rules/boxels/cursor-rules/design"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/design/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/rules/boxels/cursor-rules/design"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/design.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 | $0.01681 | $0.01681 |
| Opus 5 | $0.00840 | $0.00840 |
| Sonnet 5 | $0.00336 | $0.00336 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
design 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 yesterday.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Rules
Component library
- [Base component library, e.g. "shadcn/ui", "Material UI", "Ant Design", "Vuetify", "DaisyUI", "custom components"]. Extend existing components — never rebuild from scratch what the library already provides.
- Icons: [icon set, e.g. "Lucide React", "Heroicons", "Material Icons", "Font Awesome"]. [Defaults, e.g. "20px default size, 1.5px stroke weight."]
- Animations: [animation library, e.g. "Framer Motion", "GSAP", "CSS transitions only", "Svelte transitions"]. [Constraint, e.g. "Max 300ms for UI transitions. No animations on first paint."]
- Dropdowns, popovers, and overlays: [approach, e.g. "Radix primitives via shadcn", "Headless UI", "native library components"]. Must have proper keyboard navigation and dismiss on outside click.
- Dialogs: [approach, e.g. "shadcn Dialog", "Material Dialog", "custom modal component"]. Never use alert(), window.confirm(), or browser-native dialogs.
- Searchable dropdowns / autocomplete pickers: never ship mouse-only. Required keys — see Patterns below.
States
Every interactive component must account for all of its states. Don't ship a "happy path only" UI.
- Loading: Every async operation needs a loading indicator. [Approach, e.g. "Skeleton loaders for content areas", "Spinner inside buttons during actions", "Progress bars for uploads"]. Never show blank screens while data loads.
- Empty: Every list, table, and feed needs a designed empty state — [approach, e.g. "illustration + message + call-to-action", "helpful prompt to get started", "minimal text"]. Never show a blank container.
- Error: [Approach, e.g. "Inline error messages below fields", "Toast notifications for action failures", "Error boundaries for component crashes"]. Errors should explain what happened and offer a path forward.
- Interactive: All interactive elements need hover, focus, active, and disabled states. No element should feel unresponsive.
- Buttons: [Loading behavior, e.g. "Show spinner inside the button during async actions. Disable while loading. Never allow double-submit."]
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.
- yesterday First seen · 78 lines · 1,681 tokens per session scan A 8d607e9e9dc4
design is a cursor rule published in the GitHub repository BOXELS/cursor-rules (6 stars, last pushed yesterday), licensed MIT. It adds 1,681 tokens to every session, about $0.0084 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 2026-09-15.
Other cursor rules, from other repositories
prototype-previewer
Build interactive prototype reviewers with synced review notes and Figma capture pages.
figma-performance
Handling large documents efficiently in the Plugin API.
ant-design
A set of guidelines for using Ant Design, a collection of ready-made interface components, in React applications. It covers code organization, performance, security, testing, and common mistakes.
7-day-nextjs-web-design-cursor
A seven-day design workflow for web products that will be built in Next.js.
clone-ai
Site Clone AI — website klonlama pipeline kuralları.
mermaid
Diagram Creator. Load when the user requests "Create a diagram".