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/maquina-app/rails-claude-codenpx agentmods add skills/maquina-app/rails-claude-code/uiWrote 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/maquina-app/rails-claude-code/ui)<a href="https://agentmods.dev/skills/maquina-app/rails-claude-code/ui"><img src="https://agentmods.dev/badge/skills/maquina-app/rails-claude-code/ui/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/maquina-app/rails-claude-code/ui"><img src="https://agentmods.dev/badge/skills/maquina-app/rails-claude-code/ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01835 |
| Opus 5.5 | $0.00023 | $0.00734 |
| Sonnet 5.5 | $0.00012 | $0.00367 |
| Haiku 4.5 | $0.00006 | $0.00184 |
Grade A, and why
ui 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 2mo 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maquina UI Standards
Build production-quality Rails UIs with maquina_components — ERB partials styled with Tailwind CSS 4 and data attributes, inspired by shadcn/ui.
Verified against maquina-components 0.7.0. Upgrading an app from 0.5.x? Read upgrading-0.6.md first — 0.6.0 changed behavior silently. 0.7.0 broke nothing, but it deprecated
collapse_afteronresponsive_breadcrumbsand fixed focus-ring timing; never transitionoutline-colorin a component of your own.
Official documentation: https://maquina.app/documentation/components/
Core Rules
- Composition first — build screens from component partials and helpers; wrap repeated compositions into app-specific partials that encode your conventions.
- Data-attribute styling — components style through
data-component/data-*-partattributes; the engine CSS handles appearance. Reach for a variant or a role token first, and use Tailwind utilities for layout — grids, spacing, placement. - The layered engine — every engine rule lives in
@layer componentsflattened to specificity 0,1,0, so a utility passed ascss_classes:applies. That makes rule 2 a convention you keep, not a mechanism that keeps itself: an unintended utility silently reshapes the component. - Semantic variants — map meaning to variants (
:success,:warning,:destructive), one mapping per status domain. The danger variant is:destructiveeverywhere; sizes are:sm/:default/:lg(badge's middle size is:md; both accept the other's name as an alias). This vocabulary is canonical — the catalog defers to it. - Helpers for interactive components —
dropdown_menu,combobox,toggle_group,simple_table,pagination_nav(Pagy),empty_state,toast_flash_messages,breadcrumbs. Use_simplevariants for data-driven one-liners, block builders for custom content, partials for structural components (Card, Alert, Badge, Sidebar, Drawer). - Inline errors — field errors render next to their input (
data-form-part="error"), with a brief flash summary. Complete inputs: every field carriestype,required,maxlength,autocomplete, andinputmodewhere they apply. - Handle the zero state — every list renders an
empty_state(orempty_search_state/empty_list_state) when the collection is empty. - Icons via
icon_for— one icon system, delegating to the app'smain_icon_svg_foroverride with built-in SVG fallbacks. Understrict_icons(on by default in development and test) an unresolvable name raisesMaquinaComponents::UnknownIconError, so use a name from the roster in installation-guide.md. - Tokens carry the design — color, shape, elevation, focus and weight are all CSS variables. Use role tokens (
--surface-radius,--elevation-overlay,--focus-ring-width) to restyle a whole class of component, and a per-component escape hatch (--card-radius,--toast-shadow) to pin exactly one. A theme changes values, not selectors. One accent color moment per screen; neutrals elsewhere.
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.
- 2mo ago First seen · 96 lines · 58 tokens per session scan A a10fcfed5d01
ui is a skill published in the GitHub repository maquina-app/rails-claude-code (48 stars, last pushed 21d ago), licensed MIT. It adds 58 tokens to every session and 1,835 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
ui compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| uimaquina-app/rails-claude-code | Skill | 48 | 21d ago | MIT | A | 58 | Claude Code |
| anti-slop-designsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 34 | Claude Code |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |
| open-design-setupcompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 67 | Claude Code, Codex |
| frontend-visual-qadaymade/claude-code-skills | Skill | 1.5k | yesterday | MIT | A | 125 | Claude Code, Codex |
| prototype-webnexu-io/html-anything | Skill | 9.4k | 24d ago | Apache-2.0 | A | 24 | Claude Code, Codex |