Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/GktuOktay/ai-skillsnpx agentmods add rules/gktuoktay/ai-skills/imagegen-frontendWrote 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/gktuoktay/ai-skills/imagegen-frontend)<a href="https://agentmods.dev/rules/gktuoktay/ai-skills/imagegen-frontend"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/imagegen-frontend/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/gktuoktay/ai-skills/imagegen-frontend"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/imagegen-frontend.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 | $0.01878 |
| Opus 5 | $0.00000 | $0.00939 |
| Sonnet 5 | $0.00000 | $0.00376 |
| Haiku 4.5 | $0.00000 | $0.00188 |
Grade A, and why
imagegen-frontend 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 8d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Generation for Frontend — Web & Mobile
A unified guide for generating, integrating, and optimizing AI-created images across web and mobile frontend projects. Covers prompt engineering, asset pipeline, and platform-specific best practices.
1. Prompt Engineering for Frontend Assets
Prompt Structure Formula
[Subject] + [Style] + [Composition] + [Lighting] + [Color Palette] + [Technical Specs]
Style Presets by Use Case
Hero / Landing Page Backgrounds
Prompt pattern:
"Abstract [theme] background, smooth gradient, soft bokeh lights,
[brand color] and [accent color] palette, 16:9 aspect ratio,
high resolution, minimal, modern, clean negative space"
Example:
"Abstract geometric mesh background, smooth gradient transitions,
soft purple and indigo tones with subtle pink accents,
16:9 aspect ratio, 4K resolution, dark theme, minimal and premium feel"
App UI Illustrations (Onboarding, Empty States, Features)
Prompt pattern:
"Flat illustration of [scene/concept], [art style] style,
[2-3 colors] color scheme, clean vector look, white/transparent background,
centered composition, suitable for mobile app UI"
Example:
"Flat illustration of a person organizing tasks on a digital board,
minimal geometric style, blue and coral color scheme,
clean vector look, white background, centered, friendly and modern"
Product Mockups & Screenshots
Prompt pattern:
"[Device type] mockup displaying [UI description],
[environment/setting], professional product photography style,
soft studio lighting, shallow depth of field, [angle]"
Example:
"iPhone 15 Pro mockup displaying a fitness tracking dashboard,
on a minimal white desk with soft shadows,
professional product photography, 45-degree angle, studio lighting"
Icons & Small Assets
Prompt pattern:
"Single [object] icon, [style] style, [color] on [background],
simple, centered, 1:1 aspect ratio, suitable for app icon / UI icon"
Example:
"Single rocket icon, line art with gradient fill, purple to blue,
on transparent background, simple, centered, 1:1, modern SaaS style"
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.
- 8d ago First seen · 209 lines · 1,878 tokens per session scan A a3a1a3834e68
imagegen-frontend is a cursor rule published in the GitHub repository GktuOktay/ai-skills (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,878 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
react-best-practices
USE WHEN: Designing React components, implementing hooks, and managing component lifecycles.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.