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/kok-o/koko-contextos-agentsWrote 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/kok-o/koko-contextos-agents/ui-ux-pro)<a href="https://agentmods.dev/rules/kok-o/koko-contextos-agents/ui-ux-pro"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/ui-ux-pro/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/kok-o/koko-contextos-agents/ui-ux-pro"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/ui-ux-pro.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 | $0.00000 | $0.04106 |
| Opus 5 | $0.00000 | $0.02053 |
| Sonnet 5 | $0.00000 | $0.00821 |
| Haiku 4.5 | $0.00000 | $0.00411 |
Grade A, and why
ui-ux-pro 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: ui-ux-pro
ui-ux-pro
Overview
A brief summary of what the skill does and its core philosophy.
When to Use
Context for when this skill is applicable.
Rules & Patterns
Inspired by nextlevelbuilder/ui-ux-pro-max-skill.
Core Principle
Great design is invisible. Bad design is obvious. You will never produce obvious AI design.
Pre-flight Check & Brief Inference
Before starting a design implementation:
- Infer the unwritten constraints of the domain (e.g., if it's a dev tool, assume dark mode, monospaced numbers, dense layout).
- Propose a "Design Brief Inference" summarizing the intended aesthetic.
[FAIL] Absolute Prohibitions (Never Do These)
Typography Anti-Patterns
- NEVER use Arial, Helvetica, or system-ui defaults as primary fonts
- NEVER use Inter as the ONLY font — it is the #1 "AI-generated" visual tell when used alone
- [PASS] CORRECT: If using Inter for primary UI text, ALWAYS pair it with a strong monospace font like
JetBrains Monofor numbers, code blocks, and technical accents to create a premium SaaS aesthetic (see Vercel, Linear) - [FAIL] WRONG: Inter for headings, body, labels, numbers, captions — everything
- [PASS] CORRECT: If using Inter for primary UI text, ALWAYS pair it with a strong monospace font like
- NEVER mix more than 2 font families
- ALWAYS import proper fonts from Google Fonts or similar
Color Anti-Patterns
- NEVER use pure black
#000000— always tint toward brand hue (e.g.#0A0A0F) - NEVER use pure gray
#808080— tint it (e.g.#6B7280has blue undertones) - NEVER use purple-to-blue gradients — it is the #1 "AI generated" visual tell
- NEVER use neon colors for primary UI (only accents, sparingly)
- ALWAYS use HSL-based semantic palettes with clear naming
Layout Anti-Patterns
- NEVER nest cards inside cards (card-in-card = instant slop flag)
- NEVER put a rounded-square icon tile above every heading
- NEVER center-align long paragraphs (> 2 lines)
- NEVER use gray text on colored backgrounds (contrast failure)
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.
- 4d ago Changed · +86 lines 13f04b5aa3a8
- 6d ago First seen · 354 lines · 0 tokens per session scan A df86a93eda9b
ui-ux-pro is a cursor rule published in the GitHub repository kok-o/koko-contextos-agents (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,106 tokens. 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 2026-09-03.
Other cursor rules, from other repositories
align-grid
Build editorial/magazine/report webpages on a GENUINE Müller-Brockmann modular grid (International Typographic Style) — not a decorative one. Encodes the discipline (columns + modules + baseline, grotesque type, flush-left, restrained black/white/red palette) AND the hard-won front-end engineering to make the grid…
extract-design
Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose. Use when the user has an HTML prototype and wants a DESIGN.md to anchor their project's visual identity, or when seed-conventions has just scaffolded a…
hatch3r-design-system-detection
Mandatory detection of existing design tokens, theme primitives, and component library before AI agents author new UI components.
hatch3r-ux-states-and-flows
Four-state surface contract (loading/empty/error/partial), user-flow decomposition before implementation, and microcopy + tone discipline for end-user UIs.
hatch3r-ai-ux-patterns
2026 AI/agentic UX patterns for end-user projects shipping AI features — streaming, tool-call UI, human-approval gates, cancel/abort/undo, citations.
hatch3r-accessibility-standards
Accessibility standards covering WCAG 2.2 AA compliance, keyboard navigation, screen readers, and ARIA patterns.