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 AdamBien/airails --skill web-sprinklesgit clone --depth 1 https://github.com/AdamBien/airailsWrote 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/adambien/airails/web-sprinkles)<a href="https://agentmods.dev/skills/adambien/airails/web-sprinkles"><img src="https://agentmods.dev/badge/skills/adambien/airails/web-sprinkles/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/adambien/airails/web-sprinkles"><img src="https://agentmods.dev/badge/skills/adambien/airails/web-sprinkles.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 | $0.00224 | $0.02126 |
| Opus 5.5 | $0.00090 | $0.00850 |
| Sonnet 5.5 | $0.00045 | $0.00425 |
| Haiku 4.5 | $0.00022 | $0.00213 |
Grade A, and why
web-sprinkles 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 1mo 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build or maintain a static site with JavaScript enhancements using $ARGUMENTS. Apply all rules below strictly.
Composition
This skill is /web-static plus a bounded amount of JavaScript. Everything in /web-static applies
unchanged — CSS-only interactive patterns, CSS reset, page transitions, performance rules, project
structure, and the verification loop — except its no-JavaScript hard constraint, which this skill
replaces with the Enhancement Contract below.
/web-conventions— semantic HTML, accessibility, modern CSS, design tokens, Baseline policy/javascript-conventions— modules, syntax, collections, asynchrony, errors, JSDoc types, and the Baseline lookup for JavaScript features/web-static— everything above the JavaScript line/web-latestmay be composed on top for experiments and PoCs
Rules in this skill override all of them.
Enhancement Contract
- every page is complete and usable with zero JavaScript — content readable, navigation traversable, forms submittable and validated by the browser
- JavaScript only adds behavior to markup that already exists; it never produces the content that is the page's purpose
- links keep real
hrefs and forms keepaction/method— navigation and submission never depend on a script - a module that fails — throws, 404s, hits an unsupported API — degrades the page to its no-script baseline, never to a broken page
- enhancements are independent: one module failing must not disable the others
- nothing renders late — no content flashes in, moves, or is replaced after load
The Cut Line
If HTML or CSS can express it, a script is a defect, not a choice. Before writing one, ask what the page looks like with it removed; if the answer is "broken", the design is wrong, not the script.
| Behavior | Verdict |
|---|---|
| Accordion, disclosure | <details>/<summary> — no script |
| Tabs, hamburger, dropdown | :checked + siblings, :focus-within — no script |
| Modal | :target — no script; <dialog> plus a script only when focus trapping and Esc matter |
| Form validation | input types and constraint attributes — a script only for rules markup cannot express |
| Page transitions, smooth scroll, carousels | @view-transition, scroll-behavior, scroll snap — no script |
| Theme toggle that persists | script — CSS cannot read localStorage |
| Clipboard | script — navigator.clipboard |
| Filter, sort, or search over content already in the DOM | script |
| Locale or relative time formatting | script — Intl over a <time datetime> already in the HTML |
| Loading supplementary data | script — but content the page exists to show stays in the HTML |
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.
- 1mo ago First seen · 174 lines · 224 tokens per session scan A d115fb77a06a
web-sprinkles is a skill published in the GitHub repository AdamBien/airails (59 stars, last pushed yesterday), licensed MIT. It adds 224 tokens to every session and 2,126 once invoked, about $0.0009 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.
Other skills, from other repositories
design-context-extract
Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…
figma-design-handoff
Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to CSS Flexbox/Grid mapping, and visual regression with Applitools. Use when converting Figma designs to code, documenting component specs, setting up design-dev…
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…
animation-motion-design
Animation and motion design patterns using Motion library (formerly Framer Motion) and View Transitions API. Use when implementing component animations, page transitions, micro-interactions, gesture-driven UIs, or ensuring motion accessibility with prefers-reduced-motion.
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…
responsive-patterns
Responsive design with Container Queries, fluid typography, cqi/cqb units, subgrid, intrinsic layouts, foldable devices, and mobile-first patterns for React applications. Use when building responsive layouts or container queries.