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 | $0.00112 | $0.01063 |
| Sonnet 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 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 — 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.
- 9d ago First seen · 174 lines · 224 tokens per session scan A d115fb77a06a
web-sprinkles is a skill published in the GitHub repository AdamBien/airails (49 stars, last pushed yesterday), licensed MIT. It adds 224 tokens to every session and 2,126 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.
chat-formatting-widgets
Governs the custom markdown widgets rendered in the QuantumByte chat interface. This includes the inline highlight-mark span (use on every question the user must answer). You must check this skill on every reply to format highlights.
aksel-spacing
Lag responsive layouts med Aksel Design System (v8+) - spacing tokens, layout primitives (Box, HStack, VStack, HGrid, Page, Bleed) og ResponsiveProp.
web-design-reviewer
Visuell inspeksjon av nettsider for å identifisere og fikse designproblemer. Trigges av forespørsler som "sjekk designet", "gå gjennom UI-en", "fiks layouten", "finn designfeil". Finner problemer med responsivt design, tilgjengelighet, visuell konsistens og layout, og fikser dem i kildekoden.
design-shiny-ui
Design Shiny application UIs using bslib for theming, layoutcolumns for responsive grids, value boxes, cards, and custom CSS/SCSS. Covers page layouts, accessibility, and brand consistency. Use when building a new Shiny app UI from scratch, modernizing an existing app from fluidPage to bslib, applying brand theming…