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 roedyrustam/vibes-plug --skill svelte-sveltekit-expertgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/roedyrustam/vibes-plug/svelte-sveltekit-expert)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/svelte-sveltekit-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/svelte-sveltekit-expert/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/roedyrustam/vibes-plug/svelte-sveltekit-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/svelte-sveltekit-expert.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 | $0.00091 | $0.04409 |
| Opus 5.5 | $0.00036 | $0.01764 |
| Sonnet 5.5 | $0.00018 | $0.00882 |
| Haiku 4.5 | $0.00009 | $0.00441 |
Grade A, and why
svelte-sveltekit-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Svelte 5 & SvelteKit 2 Expert (Runes Standard 2026)
English
Orchestration & Integration
- Upstream System Design:
brainstorming,zero-to-prod-orchestrator(Phase 3 & Phase 4). - Styling & Web Standards:
modern-web-guidance,tailwind-expert,modern-css-native-expert,design-system-architect. - Quality & Performance:
performance-web-vitals,e2e-testing-expert,anti-slop,visual-ui-auditor. - Backend & APIs:
js-backend-expert,database-orm-expert,typescript-expert.
Description
Production-grade guide for building high-performance web applications using Svelte 5 and SvelteKit 2+. Covers the complete Runes reactivity paradigm ($state, $derived, $derived.by, $effect, $props, $bindable), snippet composition replacing legacy slots, progressive enhancement form actions (use:enhance), streaming server promises in +page.server.ts, and shallow routing (pushState) for modal overlays.
Trigger Conditions
- Scaffolding new applications with Svelte 5 and SvelteKit 2.
- Refactoring legacy Svelte 3/4 reactive declarations (
let x = 0; $: doubled = x * 2;) to Svelte 5 Runes. - Composing modular UI components using Svelte 5 Snippets instead of legacy
<slot>. - Implementing form submissions with atomic server actions and zero-JS progressive enhancement.
- Streaming large asynchronous datasets to the client without blocking the initial SSR HTML payload.
Core Architectural Patterns
1. Complete Svelte 5 Runes Reference
| Rune | Purpose | Svelte 4 Legacy Syntax |
|---|---|---|
$state(val) |
Deeply reactive state proxy | let val = ... |
$state.raw(val) |
Shallow reactive state (ideal for immutable/large payloads) | N/A |
$derived(expr) |
Cached reactive derivation | $: val = expr |
$derived.by(() => {}) |
Complex multi-line derived computation | $: { ... } |
$effect(() => {}) |
Post-DOM mount & update side-effect with cleanup | onMount, afterUpdate, $: { ... } |
$effect.pre(() => {}) |
Pre-DOM update effect (e.g. scroll position capture) | beforeUpdate |
$props() |
Type-safe destructured component props | export let prop |
$bindable() |
Explicit two-way prop binding allowance | Direct two-way binding |
$inspect(val) |
Automatic dev-mode deep state inspector | console.log(val) in $: |
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.
- 6d ago Changed · +261 lines · +4 tokens per session d564494b2658
- 7d ago Changed · +1 lines 23f11d36d853
- 10d ago Changed · +108 lines e0ca89b314d7
- 19d ago Changed 18d2212c3d6f
- 24d ago Changed 50c2549d6aca
- 25d ago Changed 6e52aebc0c2f
- 27d ago Changed · -6 lines · +70 tokens per session a048f0d5a696
- 29d ago Changed · +6 lines · -70 tokens per session bad365abc3ac
- 1mo ago Changed 26f00d0e7914
- 1mo ago First seen · 92 lines · 87 tokens per session scan A 829cbba6f4da
svelte-sveltekit-expert is a skill published in the GitHub repository roedyrustam/vibes-plug (115 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 4,409 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
artisan
Implementing production frontend code for React/Vue/Svelte: hooks design, state management, Server Components, form handling, data fetching. Converts Forge prototypes to production quality.
vuetify
Expert Vuetify assistance covering Material Design components, data tables, responsive layouts, and themes for Vue 3. Use when rapidly building enterprise dashboards and back-office tools in Vue.
nuxt
Expert Nuxt 3 assistance covering Vue 3, auto-imports, file-based routing, Nitro server engine, and universal rendering. Use when developing SEO-optimized full-stack Vue applications.
vue
Expert Vue 3 assistance covering Composition API ( ), reactivity (ref, reactive), Pinia, and Vue Router. Use when developing modern, progressive web interfaces and single-page applications.