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.
npx agentmods add skills/zhpeng24/devkit/imagegen-frontend-webnpx skills add zhpeng24/devkit --skill imagegen-frontend-webgit clone --depth 1 https://github.com/zhpeng24/devkitWrote 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/skills/zhpeng24/devkit/imagegen-frontend-web)<a href="https://agentmods.dev/skills/zhpeng24/devkit/imagegen-frontend-web"><img src="https://agentmods.dev/badge/skills/zhpeng24/devkit/imagegen-frontend-web.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00502 |
| Opus 5 | $0.00017 | $0.00251 |
| Sonnet 5 | $0.00007 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
imagegen-frontend-web 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 3d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Web Image Generation
Generate implementation-readable website references, not code and not generic mood art. Stop after delivering the requested images.
Set the scope
Read the page purpose, audience, brand material, content, viewport, requested sections, and intended downstream use. Existing brand assets and approved references are authoritative.
Choose the smallest image set that makes the requested design readable:
- one requested hero remains one image;
- separate sections when combining them would make type, spacing, or controls hard to inspect;
- do not expand an unspecified request into an arbitrary six- or eight-section site;
- if a full flow is genuinely required, name the sections before generation.
Establish one design bible
Keep palette, typography, spacing, radii, borders, imagery treatment, icon style, and tone consistent across the set. Give each section a clear job—hook, explain, prove, compare, or convert—while varying composition intentionally.
Avoid default purple-blue AI gradients, repeated left-copy/right-image sections, equal card rows, nested rounded boxes, decorative pills, fake dashboards, fake logos, testimonials, metrics, or awards. Use only supplied facts and assets with known rights.
Generate
Use the available image-generation capability. Each prompt should identify:
- exact section and viewport;
- hierarchy and short readable copy;
- grid, focal point, negative space, and CTA placement;
- palette, type character, media treatment, and surface details;
- continuity rules shared with the rest of the set;
- implementation constraints such as visible controls and realistic proportions.
Keep text sparse enough to remain legible. Prefer a fresh standalone image over cropping an earlier render when a section or detail needs its own reference.
Check and deliver
Inspect every image for readable type, coherent hierarchy, consistent system, unclipped content, plausible website geometry, useful implementation detail, and brand continuity. Regenerate only failed frames.
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.
- 3d ago First seen · 47 lines · 35 tokens per session scan A ddf0f8ca1f2a
imagegen-frontend-web is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 502 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
better-ui
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, enter/exit animations, choosing or reviewing icons, or any visual detail work. Triggers on UI polish, design details…
nano-banana
Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing. Full workflow: content planning conversation → slidesplan.json → batch image generation → review with feedback → targeted slide…
feishu-cli-visual
飞书可视化与展示统一入口，负责选择合适载体，并覆盖画板、Slides、妙笔BOX 动态组件、 妙搭 HTML 应用和统一数据可视化设计规范。用户要求画板/whiteboard、架构图、流程图、飞轮、 鱼骨、路线图、海报、插画、SVG/Mermaid、数据图表或 dashboard，创建 Slides/PPT，嵌入会动的 ECharts/地图/3D/window.magic 组件，或用妙搭/Miaoda/spark 发布 HTML 应用时必须使用本 Skill。 消息卡片由 feishu-cli-messaging 构造和发送；Markdown 图表导入由 feishu-cli-docs 执行。.
render-vo-anchored-motion-listicle
Assemble an expert/educator motion-graphic LISTICLE video ad from a config — a spoken authoritative voiceover carries a numbered listicle while N web-animated hyperframe beats (HTML plus the Web Animations API, one branded design system of alternating tiles, big hero numerals, and glass-pill callouts) are rendered…