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 agentmods add rules/travishorn/cursor-rules-sveltekit/svelte-5git clone --depth 1 https://github.com/travishorn/cursor-rules-sveltekitWrote 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/travishorn/cursor-rules-sveltekit/svelte-5)<a href="https://agentmods.dev/rules/travishorn/cursor-rules-sveltekit/svelte-5"><img src="https://agentmods.dev/badge/rules/travishorn/cursor-rules-sveltekit/svelte-5.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.03352 |
| Opus 5 | $0.00000 | $0.01676 |
| Sonnet 5 | $0.00000 | $0.00670 |
| Haiku 4.5 | $0.00000 | $0.00335 |
Grade A, and why
svelte-5 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 5d 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 — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Svelte 5
This project uses the newer Svelte 5 instead of the more common Svelte 4.
Version 5 comes with an overhauled syntax and reactivity system. While it may look different at first, you'll soon notice many similarities. This guide goes over the changes in detail and shows you how to upgrade. Along with it, we also provide information on why we did these changes.
Reactivity syntax changes
At the heart of Svelte 5 is the new runes API. Runes are basically compiler instructions that inform Svelte about reactivity. Syntactically, runes are functions starting with a dollar-sign.
let → $state
In Svelte 4, a let declaration at the top level of a component was implicitly reactive. In Svelte 5, things are more explicit: a variable is reactive when created using the $state rune. Let's migrate the counter to runes mode by wrapping the counter in $state.
Old, Svelte 4 syntax:
<script>
let count = 0;
</script>
New, Svelte 5 syntax:
<script>
let count = $state(0);
</script>
Nothing else changes. count is still the number itself, and you read and write directly to it, without a wrapper like .value or getCount().
$: → $derived/$effect
In Svelte 4, a $: statement at the top level of a component could be used to declare a derivation, i.e. state that is entirely defined through a computation of other state. In Svelte 5, this is achieved using the $derived rune.
Old, Svelte 4 syntax:
<script>
let count = 0;
$: double = count * 2;
</script>
New, Svelte 5 syntax:
<script>
let count = $state(0);
const double = $derived(count * 2);
</script>
As with $state, nothing else changes. double is still the number itself, and you read it directly, without a wrapper like .value or getDouble().
Sometimes you need to create complex derivations that don't fit inside a short expression. In these cases, you can use $derived.by which accepts a function as its argument.
<script>
let numbers = $state([1, 2, 3]);
let total = $derived.by(() => {
let total = 0;
for (const n of numbers) {
total += n;
}
return total;
});
</script>
<button onclick={() => numbers.push(numbers.length + 1)}>
{numbers.join(' + ')} = {total}
</button>
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.
- 5d ago First seen · 574 lines · 0 tokens per session scan A 66519091b45f
svelte-5 is a cursor rule published in the GitHub repository travishorn/cursor-rules-sveltekit (9 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,352 tokens. 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 2026-08-31.
Other cursor rules, from other repositories
svelte-5-vs-svelte-4-cursorrules-prompt-file
Cursor rules for comparing Svelte 5 and Svelte 4 development.
sveltekit-typescript-guide-cursorrules-prompt-file
Cursor rules for SvelteKit development with TypeScript integration.
vue-typescript-patterns
Cursor rule "vue-typescript-patterns" from soaring-xiongkulu/easyaiot, covering vue3 + typescript 开发规范, vue 组件规范, vue sfc 组件规范, typescript 规范 and 状态管理.
svelte-mcp-tools
Instructions for using the Svelte MCP server tools for documentation lookup, code analysis, and validation.
frontend-component
Vue component structure, styling, derived state, modals, icons, DaisyUI/Tailwind frontend component conventions.
frontend
Vue frontend — components, Vitest, generated API client, apiCallWithLoading, DaisyUI. Read this first for any frontend work.