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 skills add rob-balfre/dryui --skill variant-c-decision-tablegit clone --depth 1 https://github.com/rob-balfre/dryuiWrote 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/rob-balfre/dryui/variant-c-decision-table)<a href="https://agentmods.dev/skills/rob-balfre/dryui/variant-c-decision-table"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/variant-c-decision-table/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/skills/rob-balfre/dryui/variant-c-decision-table"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/variant-c-decision-table.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 | $0.00035 | $0.00703 |
| Opus 5 | $0.00017 | $0.00351 |
| Sonnet 5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
dryui-build-experiment-c 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 9d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DryUI Build Experiment C: Decision Tables
Classify The Request
| If the user asks for | Build as | First recipe |
|---|---|---|
| route, screen, dashboard, admin, settings, page | full page | Page recipe |
| hero, pricing, table area, sidebar, header, footer | section | Section recipe |
| card, row, item, badge group, cell | component fragment | Component recipe |
| form, wizard, editor, settings flow | workflow | Workflow recipe |
| make nicer, polish, improve layout | review/refine | Review recipe |
If the page contains tables, charts, metrics, filters, or admin work, also apply the Dashboard recipe.
Page Recipe
- Root: one semantic route root with
data-layout="<route-name>". - Container: root declares
container: <route-name> / inline-sizeinsrc/layout.css. - Areas: direct structural children use
data-layout-area. - Layout CSS:
src/layout.cssonly. - Responsive: mobile base plus
@container <route-name> (...). - Prohibited in component styles:
display: grid,display: flex,@medialayout breakpoints, inline style, Sveltestyle:. - Verification: mobile, desktop, long text, and no horizontal overflow.
Dashboard Recipe
| Decision | Rule |
|---|---|
| Primary purpose | Pick one: monitor, compare, triage, report, configure, act. |
| Density | Pick compact for admin/data, standard for mixed content, spacious only for executive summary. |
| Regions | Header, action/filter bar, KPI summary, primary visualization, data table, secondary detail if needed. |
| Dominance | Primary visualization or table gets the largest stable grid area. |
| Cards | Use for KPIs or comparable units only; do not scaffold the page with cards. |
| Data | Use DataGrid/Table and Chart/Sparkline when available. |
| States | Default, loading, empty, error, disabled, dense rows, long labels. |
| Mobile | Collapse to one column; keep filters/actions before affected data. |
What ships with it
1 file 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.
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.
- 9d ago First seen · 74 lines · 35 tokens per session scan A 542f4bee7f88
dryui-build-experiment-c is a skill published in the GitHub repository rob-balfre/dryui (9 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 703 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
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…
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json…
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
anti-ui-slop
Stop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.
design
Use when the user wants the visual/experiential design of a product done systematically — a design system, a screen, a landing page, or a visual identity — grounded in researched real-world prior art and free of AI slop. Establishes/extends the design system, invokes the matching local taste skill, dispatches the…
shadcn-ui-flutter
A comprehensive Flutter UI library inspired by shadcn/ui. Provides high-quality, customizable, and accessible components including Buttons, Cards, Forms, and more. Use this skill when building Flutter UIs, implementing design systems, or needing specific component usage examples.