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.
git clone --depth 1 https://github.com/nedcodes-ok/cursorrules-collectionWrote 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/rules/nedcodes-ok/cursorrules-collection/sveltekit)<a href="https://agentmods.dev/rules/nedcodes-ok/cursorrules-collection/sveltekit"><img src="https://agentmods.dev/badge/rules/nedcodes-ok/cursorrules-collection/sveltekit/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/rules/nedcodes-ok/cursorrules-collection/sveltekit"><img src="https://agentmods.dev/badge/rules/nedcodes-ok/cursorrules-collection/sveltekit.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 | $0.00510 | $0.00510 |
| Opus 5.5 | $0.00204 | $0.00204 |
| Sonnet 5.5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
sveltekit 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SvelteKit Cursor Rules
You are an expert SvelteKit developer. Follow these rules:
Routing & Files
- Use file-based routing: +page.svelte, +layout.svelte, +page.server.ts, +page.ts
- Server-only logic in +page.server.ts (DB queries, secrets). Universal load in +page.ts
- Group related routes with (group) folders for shared layouts without URL segments
- Use +error.svelte at layout boundaries for error UI
Load Functions
- Return typed data from load functions. Use satisfies PageLoad / PageServerLoad
- Throw error(404) or redirect(303, '/path') — never return error objects manually
- Use depends() to declare custom invalidation keys
- Avoid waterfalls: use Promise.all() for parallel data fetching in load
- Access parent layout data with await parent() — but minimize usage to avoid coupling
Form Actions
- Use form actions (+page.server.ts actions) for mutations, not API routes
- Default action for single forms, named actions for multiple: ?/create, ?/delete
- Return fail(422, { errors }) for validation errors — access via form prop in +page.svelte
- Use enhance for progressive enhancement: use:enhance on all forms
- After successful mutation, data reloads automatically — don't manually invalidate
Components
- Props via export let for Svelte 4, $props() rune for Svelte 5
- Reactive statements: $: for Svelte 4, $derived/$effect for Svelte 5
- Use {#each items as item (item.id)} — always provide a key
- Slots for composition in Svelte 4, snippets in Svelte 5
State & Stores
- Use $app/stores for page, navigating, updated stores
- Writable stores for shared client state. Don't put server data in stores
- Context API (setContext/getContext) for component tree data passing
- Avoid global mutable state — SSR means shared state leaks between requests
Performance
- Use streaming with promises in load functions for non-critical data
- Preload data with data-sveltekit-preload-data="hover" on links
- Static pages: export const prerender = true where applicable
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 · 47 lines · 510 tokens per session scan A 25010c2543ae
sveltekit is a cursor rule published in the GitHub repository nedcodes-ok/cursorrules-collection (38 stars, last pushed 7mo ago), licensed MIT. It adds 510 tokens to every session, about $0.0020 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 cursor rules, from other repositories
vue3-typescript-auto
Vue 3 with TypeScript Standards.
23-app-startup
Application class, SplashScreen, StartupActivity + MainActivity split, and AndroidX Startup.
29-screen-startup
StartupActivity funnel — StartupFragment init/routing, Startup screens, hand-off to MainActivity.
03-android-architecture
Clean Architecture layer rules.
12-naming-conventions
Cross-cutting naming conventions reference — Kotlin, Gradle, packages, resources, logging, analytics, domain.
01-feature-checklist
New feature / screen scaffolding checklist — use when adding a feature, sonic-create-screen, sonic-create-mvi, sonic-create-clean-architecture, or verifying a feature is complete.