A product-design guide for turning rough wireframes into mid-fidelity screens. Mid-fidelity means screens with defined layout, spacing, text styles, components, and interaction states but limited visual branding.

Use it to specify screen layouts, reusable components, loading and error states, design tokens, and accessibility notes.

It removes uncertainty about structure and behavior before the final visual design is made.

04-midfi — Cursor rule for Cursor by luiscielak

Install

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.

Clone the repo

git clone --depth 1 https://github.com/luiscielak/ai-product-design-rules

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/luiscielak/ai-product-design-rules/04-midfi/github.svg)](https://agentmods.dev/rules/luiscielak/ai-product-design-rules/04-midfi)

Your own site

<a href="https://agentmods.dev/rules/luiscielak/ai-product-design-rules/04-midfi"><img src="https://agentmods.dev/badge/rules/luiscielak/ai-product-design-rules/04-midfi/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/luiscielak/ai-product-design-rules/04-midfi"><img src="https://agentmods.dev/badge/rules/luiscielak/ai-product-design-rules/04-midfi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 771 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00041	$0.00771
Opus 5.5	$0.00016	$0.00308
Sonnet 5.5	$0.00008	$0.00154
Haiku 4.5	$0.00004	$0.00077

Measured 5d ago against content hash ec23e01f2362, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

04-midfi 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 5d 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.

.cursor/rules/04-midfi.mdc · 50 lines

What it actually says

Product Designer → Generate Mid-Fidelity Wireframes

Command: /midfi
Role: Product Designer
Purpose: Define structure, hierarchy, and interaction states; introduce systemized spacing and type; still minimal visual brand.
Prerequisites: Lo-fi wireframes should exist (design/wireframes/lofi/). If missing, ask user if they want to create lo-fi first or proceed with provided inputs.
Required Inputs:
- screens (from lo-fi, or list of screen names)
- states (default: ["default", "hover", "focus", "disabled", "loading", "error", "success"])
- content_examples (short/long text variations)
- accessibility_targets (default: "WCAG AA")
Behavior:
- Read lo-fi wireframes to understand structure and flows
- Convert each lo-fi screen into mid-fi with componentized layout, spacing scale, and type scale
- Provide a token spec aligned to Tailwind and shadcn defaults
- Generate a mid-fi ui.html overview that previews each screen in device frames: a phone frame for mobile and a browser frame for desktop
- Note: When working within a project directory, use relative paths
Output:
- Directory: design/wireframes/midfi/ (relative to project directory)
- Files:
  - tokens.md (design foundations)
  - components.md (component variants/states)
  - screens/<screen-name>.md (annotated frames and interactions, one per screen)
  - ui.html (mid-fi overview page linking tokens/components/screens, showing each screen in phone and browser device frames)
- tokens.md includes:
  - Spacing: 0, 2, 4, 6, 8, 12, 16, 24, 32 (map to Tailwind: 0, 0.5, 1, 1.5, 2, 3, 4, 6, 8)
  - Typography: text-xs/sm/base/lg/xl/2xl; line-heights; weights (400, 500, 600, 700)
  - Color: neutrals, brand, semantic (map to Tailwind + shadcn themes)
  - Radius: sm/md/lg/full; Shadows: sm/md/lg
- components.md:
  - Inventory: Button, Input, Select, Card, Dialog, Sheet, Toast, Tabs, Pagination, Table, Navbar, Sidebar
  - Each component includes: anatomy, states, props, interactions, keyboard navigation, focus order
- screens/<screen-name>.md:
  - Frame description (grid, layout, spacing)
  - Component instances with props
  - State table (default/hover/focus/disabled/loading/error/success)
  - Transitions and error handling
  - Responsive behavior notes
Acceptance:
- All interactive elements have defined states and focus styles
- Accessibility notes for color contrast and keyboard support included
- Each screen preview includes device frames: phone (mobile) and browser (desktop) in ui.html
- Tokens are mappable to Tailwind/shadcn without refactoring
- All screens from lo-fi are represented

Changes

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.

5d ago First seen · 50 lines · 41 tokens per session scan A ec23e01f2362

Subscribe to this mod's changes

04-midfi is a cursor rule published in the GitHub repository luiscielak/ai-product-design-rules (4 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 771 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.

Design and UX

04-midfi

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Product Designer → Generate Mid-Fidelity Wireframes

What this file has done since we first saw it

Other cursor rules, from other repositories

prototype-previewer

figma-performance

ant-design

7-day-nextjs-web-design-cursor

clone-ai

mermaid