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 fubits1/svelte-skills --skill code-style-sveltegit clone --depth 1 https://github.com/fubits1/svelte-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/fubits1/svelte-skills/code-style-svelte)<a href="https://agentmods.dev/skills/fubits1/svelte-skills/code-style-svelte"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/code-style-svelte/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/fubits1/svelte-skills/code-style-svelte"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/code-style-svelte.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 | $0.00050 | $0.02090 |
| Opus 5.5 | $0.00020 | $0.00836 |
| Sonnet 5.5 | $0.00010 | $0.00418 |
| Haiku 4.5 | $0.00005 | $0.00209 |
Grade C, and why
code-style-svelte scanned grade C with 1 finding 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 11d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
Svelte supports standard HTML comments in component markup. `<!-- stylelint-disable -->`, `<!-- svelte-ignore ... -->`, and other tool-control comments work in `.svelte` files. `frontend:editing` decides when `svelte-ign How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Svelte Code Style
REQUIRED SUB-SKILL: invoke svelte-5:composition-svelte before you build or restructure a complex feature (wrapper or provider components, snippet APIs, shared state, third-party DOM bridging).
Ask the user whether to invoke svelte-5:composition-svelte to refactor a component when either holds:
- its
.sveltefile is longer than 300 lines, not counting its<style>block - it is complex enough that it should be split into several files
Optional snippet rendering
Use {@render snippet?.()} instead of {#if snippet}{@render snippet()}{/if}. The optional chaining form is shorter and idiomatic Svelte 5.
No $effect for setting state
NEVER use $effect to set state. If you need derived state, use $derived instead. Effects that write to state create unnecessary re-renders and are a sign of wrong reactive design.
No bare async in onMount or $effect
NEVER pass an async function directly to onMount or $effect:
// BAD — cleanup function is lost, dependency tracking breaks
onMount(async () => { ... });
$effect(async () => { ... });
// GOOD — async IIFE inside a sync wrapper
onMount(() => {
(async () => { ... })();
return () => { /* cleanup */ };
});
Two reasons:
- Cleanup is lost. Both
onMountand$effectexpect the callback to optionally return a teardown function. Anasyncfunction always returns aPromise, so the teardown never runs: intervals won't clear, subscriptions won't unsubscribe, listeners won't detach. - Dependency tracking breaks (
$effectonly).$effecttracks reactive dependencies that are read synchronously. Anything read after anawaitis invisible to the tracker and won't trigger re-runs.
No addEventListener / removeEventListener
NEVER use addEventListener or removeEventListener in Svelte components. Svelte 5 has multiple declarative mechanisms for event handling, on* attributes, callback props, svelte:window, svelte:document, svelte:body, and the on action from svelte/events. These handle cleanup automatically and integrate with Svelte's reactivity.
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.
- 11d ago Changed · +7 lines e3aaeb8b2f92
- 12d ago Changed · +9 lines · +10 tokens per session 0d7cf1b66947
- 2mo ago First seen · 118 lines · 40 tokens per session scan C abe11abce8ac
code-style-svelte is a skill published in the GitHub repository fubits1/svelte-skills (10 stars, last pushed 12d ago), licensed MIT. It adds 50 tokens to every session and 2,090 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
code-style-svelte compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-style-sveltefubits1/svelte-skills | Skill | 10 | 12d ago | MIT | C | 50 | Claude Code |
| shadcn-sveltevercel-labs/json-render | Skill | 19k | 2d ago | Apache-2.0 | A | 63 | Claude Code, Codex |
| add-localizationmicrosoft/power-platform-skills | Skill | 1.1k | yesterday | MIT | A | 69 | Claude Code |
| vue-router-best-practicesvuejs-ai/skills | Skill | 3.3k | 14d ago | MIT | A | 25 | Claude Code, Codex |
| moai-domain-uiuxmodu-ai/moai-adk | Skill | 1.3k | 4d ago | Apache-2.0 | A | 49 | Claude Code |
| moai-domain-frontendmodu-ai/moai-adk | Skill | 1.3k | 4d ago | Apache-2.0 | A | 54 | Claude Code |
| frontend-conventionsfpindej/netrock | Skill | 235 | 4d ago | MIT | A | 27 | Claude Code |