dryui-build

dryui-build is a skill for Codex from rob-balfre/dryui. It costs 62 tokens per session (6,092 once invoked), scanned C, original, MIT.

A set of instructions for building and editing Svelte 5 user interfaces with DryUI components. Svelte is a framework for building web interfaces, and DryUI provides the components, layout rules, theme settings, and accessibility guidance used here.

In plain words
What is it for?
Use it to create or modify Svelte pages, routes, forms, dashboards, components, layouts, and visual details in projects that use DryUI.
Why use it?
It gives UI changes a consistent structure and keeps them aligned with DryUI's styling and accessibility rules. It also helps avoid patterns that the project's checks reject.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; names the TodoWrite tool.

Good fit Use it to create or modify Svelte pages, routes, forms, dashboards, components, layouts, and visual details in projects that use DryUI.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rob-balfre/dryui/dryui-build
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 dryui-build
Clone the repo
git clone --depth 1 https://github.com/rob-balfre/dryui

Made for: 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/dryui-build/github.svg)](https://agentmods.dev/skills/rob-balfre/dryui/dryui-build)
Your own site
<a href="https://agentmods.dev/skills/rob-balfre/dryui/dryui-build"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/dryui-build/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/dryui-build"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/dryui-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,092 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00062 $0.06092
Opus 5 $0.00031 $0.03046
Sonnet 5 $0.00012 $0.01218
Haiku 4.5 $0.00006 $0.00609

Measured 8d ago against content hash 94a8772b2ea2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

dryui-build scanned grade C with 1 finding 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/check-component.mjs, scripts/visual-smoke.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

- No `<!-- svelte-ignore css_unused_selector -->` or other ignore comments. Fix the underlying issue.
skills/dryui-build/SKILL.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DryUI Build

Build real Svelte 5 UI with DryUI. This skill is only for UI implementation and polish. It does not install DryUI, scaffold projects, run live feedback, or resolve feedback submissions.

DryUI Contract Detection

If a project imports @dryui/ui, has src/layout.css, or enables @dryui/lint, this skill dominates UI decisions for that scope. Keep DryUI primitives, data-layout hooks, theme tokens, and lint boundaries in charge even if another framework pattern or generic Svelte habit seems faster.

Lint Rules — Read First

These are the rules @dryui/lint enforces. They are the contract — if lint, the Svelte compiler, or component metadata disagrees with a visual idea, restructure the markup or CSS instead of bypassing the rule. Bulk-silencing lint produces unstyled, broken pages because the rules and src/layout.css are coupled.

Banned in .svelte files

  • No :global(). Use scoped styles, data-* attributes, CSS custom properties, or component props.
  • No !important. Fix specificity at the source.
  • No all: unset. Reset only the specific properties you need.
  • No <svelte:element this={x}>. Use explicit {#if}/{:else} branches with concrete tags. The <!-- dryui-allow svelte-element --> escape hatch is for finite semantic tag sets only (h1-h6).
  • No <!-- svelte-ignore css_unused_selector --> or other ignore comments. Fix the underlying issue.
  • No inline style= attributes. Use scoped CSS with custom properties.
  • No style: directives. Use component props, --dry-* custom properties, or the <style> block.
  • No {@attach ...}. Use component props or CSS custom properties.
  • No leaked transcript or tool artifacts such as toolu_*, <tool_use>, <task-notification>, <subagent_notification>, TaskOutput, or TodoWrite.
  • No <a> without href. Use <button> for non-navigation actions.
  • No <hr>. Use <Separator /> so token overrides apply.
  • No raw <button>, <input>, <select>, etc. when a DryUI primitive exists. Allowed only inside the matching packages/ui/<component>/ directory.
  • No class= on DryUI components. They do not forward class to the rendered element. Use --dry-* custom properties, data-* attributes, component props, or wrap in a data-layout element. (<Button> has a back-compat className alias; most components do not.)

Read the full file on GitHub · 396 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 396 lines · 62 tokens per session scan C 94a8772b2ea2

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 62 tokens to every session and 6,092 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.