dryui-build

dryui-build is a skill for Claude Code, Codex from rob-balfre/dryui. It costs 38 tokens per session (666 once invoked), scanned A, original, MIT.

A layout-prototyping skill that builds an abstract colored-block page and checks screenshots at phone, tablet, and desktop widths. A screenshot check compares the rendered page with the intended structure.

In plain words
What is it for?
Use it to extract a design’s regions, build a mobile-first layout, run a build, inspect screenshots, and repair visible structure problems.
Why use it?
It catches responsive layout problems that may not be visible from the code or at only one screen size.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to extract a design’s regions, build a mobile-first layout, run a build, inspect screenshots, and repair visible structure problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rob-balfre/dryui/v5-visual-repair
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.

Any agent
npx skills add rob-balfre/dryui --skill v5-visual-repair
Clone the repo
git clone --depth 1 https://github.com/rob-balfre/dryui

Made for: Claude Code, Codex.

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.

agentmods badge for dryui-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/rob-balfre/dryui/v5-visual-repair/github.svg)](https://agentmods.dev/skills/rob-balfre/dryui/v5-visual-repair)
Your own site
<a href="https://agentmods.dev/skills/rob-balfre/dryui/v5-visual-repair"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/v5-visual-repair/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.

agentmods 80×15 button for dryui-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/rob-balfre/dryui/v5-visual-repair"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/v5-visual-repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 666 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00666
Opus 5 $0.00019 $0.00333
Sonnet 5 $0.00008 $0.00133
Haiku 4.5 $0.00004 $0.00067

Measured 12d ago against content hash 831563214a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dryui-build 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 12d 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.

reports/skill-experiments/2026-05-11/batch-6/v5-visual-repair/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DryUI Layout Blocks: Visual Repair Loop

Build a layout-only colored block prototype. The result is not finished UI; it is a structural proof.

Allowed edits:

  • src/routes/+page.svelte
  • src/layout.css

No imports. No @dryui/ui, Lucide, icons, SVGs, images, charts, tables, forms, buttons, inputs, avatars, cards, or real widgets.

Build Steps

  1. Extract the reference into a region list for mobile, tablet, and desktop.
  2. Decide spacing: contiguous, guttered, or mixed.
  3. Build the semantic block markup.
  4. Build mobile-first container-query layout CSS.
  5. Run bun run build.
  6. Start the app and visually check 390px, 820px, and 1440px screenshots.
  7. Repair layout if any failure gate is visible.

Shell And CSS

Use exactly:

<main data-layout="<name>-shell">
	<div data-layout-area="page">...</div>
</main>

In src/layout.css:

[data-layout='<name>-shell'] {
	container: <name> / inline-size;
}

[data-layout='<name>-shell'] [data-layout-area='page'] {
	display: grid;
	grid-template-areas:
		'topbar'
		'navigation'
		'primary'
		'secondary';
}

@container <name> (min-width: 48rem) {
}
@container <name> (min-width: 72rem) {
}

The container name and all @container names must match.

Responsive Rules

  • Base layout is mobile and one column only.
  • Tablet must be visibly different from mobile and use extra width.
  • Desktop must be visibly different from tablet and match the reference’s rails, side panels, primary surface proportions, and attached/guttered spacing.
  • If a reference has a left rail/sidebar at desktop, include it only at desktop.
  • If a reference has a dominant reader, board, form, table, or chart area, the colored primary block must be the largest region at desktop.

Visual Repair Checklist

When viewing screenshots, fix before finishing if:

  • Mobile, tablet, and desktop look like the same one-column stack.
  • Desktop misses a visible reference rail/sidebar/right inspector.
  • Primary workspace is a shallow strip.
  • Utility/activity/status blocks are larger than the main workspace.
  • Labels are clipped or illegible.
  • Page has horizontal overflow.
  • Contiguous panes show unintended white/body gaps.
  • Guttered panes lose the intended spacing.

Read the full file on GitHub · 93 lines

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.

  1. 12d ago First seen · 93 lines · 38 tokens per session scan A 831563214a11

Subscribe to this mod's changes

dryui-build is a skill published in the GitHub repository rob-balfre/dryui (9 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 666 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.

Related

Other skills, from other repositories

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality and accessible markup. Use this skill when the user asks to build or beautify web components, pages, applications, landing pages, dashboards, artifacts, or React/HTML/CSS UI. Generates creative, polished code that avoids generic AI…

spinspire/pocketbase-sveltekit-starter · 76 tokens

shadcn-sveltekit-design

Use when building, redesigning, beautifying, or refactoring SvelteKit pages and reusable components with shadcn-svelte, Bits UI, or the shadcn-svelte MCP. Trigger on landing pages, dashboards, marketing sites, app shells, forms, navbars, tables, dialogs, responsive layouts, theming, icon selection, and requests to…

Michael-Obele/shadcn-svelte-mcp · 99 tokens

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

NousResearch/hermes-agent · 23 tokens

oat-css

Our preferred CSS framework — ultra-lightweight, semantic HTML UI library (8KB). Style web UIs with semantic HTML and minimal classes. Override with app-level SCSS only when necessary.

spinspire/pocketbase-sveltekit-starter · 42 tokens

component-search

Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked results with install instructions. Use when looking for UI components, finding alternatives to existing components, or sourcing design system…

yonatangross/orchestkit · 57 tokens

polish-ui

Design-quality workflow that combines design taste, aesthetic direction, image-to-code, a Web Interface Guidelines audit, and real-browser verification. Use when building or polishing a UI surface, implementing a mockup/screenshot, or when asked to make a page "look great".

fpindej/netrock · 53 tokens