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/luiscielak/ai-product-design-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/luiscielak/ai-product-design-rules/05-hifi)<a href="https://agentmods.dev/rules/luiscielak/ai-product-design-rules/05-hifi"><img src="https://agentmods.dev/badge/rules/luiscielak/ai-product-design-rules/05-hifi/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/luiscielak/ai-product-design-rules/05-hifi"><img src="https://agentmods.dev/badge/rules/luiscielak/ai-product-design-rules/05-hifi.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 | $0.00042 | $0.00809 |
| Opus 5.5 | $0.00017 | $0.00324 |
| Sonnet 5.5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
05-hifi 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.
What it actually says
UI Designer → High-Fidelity UI Design Kit
- Command:
/hifi - Role: UI Designer
- Purpose: Deliver a comprehensive hi-fi UI design kit ready for engineering handoff, combining design system documentation with mobile-first UI designs.
- Prerequisites: Mid-fi wireframes should exist (
design/wireframes/midfi/). If missing, ask user if they want to create mid-fi first or proceed with provided inputs. - Required Inputs:
theme(light|dark|both, default: "dark")brand_color(hex/HSL format)accent_color(hex/HSL format)components(list, default: shadcn core used in project)app_concept(optional: for mobile UI design focus)key_features(optional: for mobile UI design focus)target_users(optional: for mobile UI design focus)
- Behavior:
- Read mid-fi wireframes and tokens to understand structure and design system
- Map product tokens to Tailwind/shadcn CSS variables; document color roles and states
- Generate a static component gallery with device frames (phone + browser) showing key variants and states
- Include layout density, elevation, motion, and accessibility checklists
- If mobile UI focus is requested, create mobile-first designs following design principles
- Note: When working within a project directory, use relative paths
- Design Principles (for mobile UI focus):
- Balance elegant minimalism with functional design
- Use soft, refreshing gradient colors aligned with brand palette
- Have well-proportioned white space and clean layouts
- Create light and immersive user experience
- Establish clear hierarchy through subtle shadows and modular cards
- Maintain natural focus on core functionalities
- Use refined rounded corners
- Include delicate micro-interactions
- Ensure comfortable visual proportions
- Technical Requirements (for mobile UI focus):
- Design for 375x812px mobile viewport with device frames
- Use background-free vector icons from online libraries
- Source open-source images with direct links
- Style using Tailwind CSS via CDN
- Exclude mobile status bars and system indicators
- Avoid non-mobile UI elements like scrollbars
- Use only black or white text
- Output:
- Directory:
design/ui-design/(relative to project directory) - Files:
theme.md(CSS variables and Tailwind mapping examples)color-roles.md(neutrals, brand, semantic; usage and contrast notes)component-gallery.html(interactive preview of core components in device frames)layout-guidelines.md(grid, spacing, elevation, motion)accessibility-checklist.md(WCAG AA essentials, keyboard/focus)mobile-ui-design.html(mobile-first UI designs with device frames, if mobile focus requested)
- Directory:
- Acceptance:
- Component gallery renders primary variants and states for Button, Input, Select, Checkbox, Card, Tabs, Table; Dialog preview included
- Device frames present for mobile and desktop previews
- Theme variables align with tokens and are implementable in Tailwind/shadcn without refactoring
- If mobile UI focus: horizontal
mobile-ui-design.htmlwith all app screens, following design principles and technical requirements - All color combinations meet WCAG AA contrast requirements
- Design system is complete and ready for engineering handoff
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 · 61 lines · 42 tokens per session scan A 7f8d388e2eff
05-hifi is a cursor rule published in the GitHub repository luiscielak/ai-product-design-rules (4 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 809 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.
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".