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 hamzabellouch/agent-skills --skill sveltekit-and-svelte5-runesgit clone --depth 1 https://github.com/hamzabellouch/agent-skillsWrote 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/hamzabellouch/agent-skills/sveltekit-and-svelte5-runes)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/sveltekit-and-svelte5-runes"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/sveltekit-and-svelte5-runes/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/hamzabellouch/agent-skills/sveltekit-and-svelte5-runes"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/sveltekit-and-svelte5-runes.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 | $0.00053 | $0.02362 |
| Opus 5 | $0.00026 | $0.01181 |
| Sonnet 5 | $0.00011 | $0.00472 |
| Haiku 4.5 | $0.00005 | $0.00236 |
Grade A, and why
sveltekit-and-svelte5-runes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SvelteKit & Svelte 5 Runes Architecture Guide
Core Architectural Principles
1. Svelte 5 Runes Paradigm
- Fine-Grained Signals: Svelte 5 replaces stores (
writable,readable) and compiler-magic$:declarations with deep reactive primitives (Runes). - Primitives:
$state(initial): Deeply reactive state definition. Use$state.raw(initial)for non-reactive large structures (e.g., WebGL objects, large immutable arrays).$derived(expression): Pure, memoized computational projections. Use$derived.by(() => { ... })for complex multi-statement computations.$effect(() => { ... }): Side-effect execution (DOM mutation, external sync). Must remain free of state mutations to prevent feedback loops.$props(): Component property declaration with TS interface support and default assignments.$bindable(): Explicit opt-in two-way data binding for props.
- Class-Based Reactive Stores: Encapsulate domain logic inside standard ES classes utilizing
$stateand$derivedproperties, completely eliminating legacy store boilerplate.
2. SvelteKit Data Flow & SSR Isolation
- Universal vs Server Load:
- Use
+page.server.tsfor database access, secret keys, or direct server APIs. - Use
+page.tsfor universal client/server fetching or rendering logic.
- Use
- Streaming Async Data: Return non-awaited promises in
+page.server.tsto stream slow data dependencies using SvelteKit's built-in streaming support. - Form Actions & Progressive Enhancement: Always leverage SvelteKit Form Actions with
use:enhanceto ensure forms work seamlessly with or without JavaScript enabled.
Production Code Examples
Example 1: Svelte 5 Class-Based Reactive State Store
Location: src/lib/stores/cart.svelte.ts
export interface CartItem {
id: string
name: string
price: number
quantity: number
}
export class ShoppingCartStore {
// Deeply reactive state array
items = $state<CartItem[]>([])
discountCode = $state<string | null>(null)
discountPercent = $state<number>(0)
// Derived memoized values
itemCount = $derived(this.items.reduce((total, item) => total + item.quantity, 0))
subtotal = $derived(
this.items.reduce((sum, item) => sum + item.price * item.quantity, 0)
)
tax = $derived.by(() => {
const taxableAmount = Math.max(0, this.subtotal * (1 - this.discountPercent))
return taxableAmount * 0.08 // 8% sales tax
})
total = $derived(Math.max(0, this.subtotal * (1 - this.discountPercent)) + this.tax)
addItem(newItem: Omit<CartItem, 'quantity'>) {
const existing = this.items.find(i => i.id === newItem.id)
if (existing) {
existing.quantity += 1
} else {
this.items.push({ ...newItem, quantity: 1 })
}
}
removeItem(id: string) {
this.items = this.items.filter(i => i.id !== id)
}
updateQuantity(id: string, quantity: number) {
const item = this.items.find(i => i.id === id)
if (item) {
if (quantity <= 0) {
this.removeItem(id)
} else {
item.quantity = quantity
}
}
}
applyDiscount(code: string, percent: number) {
this.discountCode = code
this.discountPercent = percent / 100
}
clear() {
this.items = []
this.discountCode = null
this.discountPercent = 0
}
}
// Global or scoped instantiations
export const cartStore = new ShoppingCartStore()
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.
- 8d ago First seen · 312 lines · 53 tokens per session scan A 9920284be4f5
sveltekit-and-svelte5-runes is a skill published in the GitHub repository hamzabellouch/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 2,362 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
fec-vue3-project-standard
A Vue 3 and TypeScript project standard covering component boundaries, composables, routing, Pinia state, API layers, errors, styles, and project structure. Vue is a frontend framework, and composables are reusable functions for sharing component logic.
cc-frontend-dev
Frontend development guidance covering Vue 3, user-interface style, and TypeScript.
typescript-react-nextjs-patterns
Production-grade TypeScript reference for React & Next.js frontend development. Covers type narrowing, component Props, generic hooks, discriminated unions, as const, satisfies, Zod validation, TanStack Query, server/client boundaries, forms, state management, performance, accessibility, debugging, and code review.…
vue3-typescript
Vue 3 with TypeScript and Composition API.
angular
Angular TypeScript framework with dependency injection and RxJS. Use for enterprise SPAs.
nuxtjs-vue-typescript
Best practices for building Nuxt 3 and Vue 3 applications with TypeScript, the Composition API, and Tailwind CSS. Use when structuring Nuxt/Vue projects, writing composables, typing components and props, wiring up server routes and plugins, or optimizing Nuxt builds and Web Vitals.