What is rc-sveltekit?

A development guide for SvelteKit 2 and Svelte 5 applications, using Bun to run the server. SvelteKit is a web framework that can render pages on the server and handle forms, sessions, and deployment.

Use it when building or changing SvelteKit routes, server-side data loading, form actions, login sessions, security hooks, or Bun-based VPS deployments. It also covers Vitest and Playwright testing.

It helps keep server-rendered data, form handling, cookies, security settings, and deployment configuration correct in one project.

rc-sveltekit — Skill for Claude Code by rodolfochicone

Install

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.

Any agent

npx skills add rodolfochicone/rc-project --skill rc-sveltekit

Clone the repo

git clone --depth 1 https://github.com/rodolfochicone/rc-project

Made for: Claude Code.

Or install rc, the plugin that ships this one along with the rest of its 32 skills, 2 commands, 4 agents, 5 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc-sveltekit/github.svg)](https://agentmods.dev/skills/rodolfochicone/rc-project/rc-sveltekit)

Your own site

<a href="https://agentmods.dev/skills/rodolfochicone/rc-project/rc-sveltekit"><img src="https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rodolfochicone/rc-project/rc-sveltekit"><img src="https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc-sveltekit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 898 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00093	$0.00898
Opus 5	$0.00046	$0.00449
Sonnet 5	$0.00019	$0.00180
Haiku 4.5	$0.00009	$0.00090

Measured 11d ago against content hash 624a0624c6d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rc-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 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.

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.

skills/stacks/rc-sveltekit/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SvelteKit 2 + Svelte 5

Full-stack UI with SSR/SEO and progressive enhancement. Target: SvelteKit 2.x, Svelte 5 (runes), adapter-node build run under Bun ≥ 1.3. Pair with rc-axum when the API is a separate Rust service.

Core workflow

Routes — file-based src/routes; prefer server load for private/SEO data.
SSR — +page.server.ts for data that must hit the API with secrets; never put secrets in PUBLIC_*.
Forms — form actions + fail() for validation; progressive enhancement.
Hooks — hooks.server.ts for session → event.locals; keep locals in sync after actions that change cookies.
Security — CSRF (built-in), cookie flags, CSP. Read references/security.md.
Deploy — adapter-node, HOST=127.0.0.1, reverse proxy. Read references/ssr-deploy.md.
Test — Vitest + Playwright as needed. Read references/testing.md.

Reference guide

Topic	File	Load when
Load, actions, layout, env	`references/guide.md`	Building routes
CSRF, cookies, CSP, XSS	`references/security.md`	Auth/sessions/public pages
adapter-node, env, VPS	`references/ssr-deploy.md`	Deploy / SSR config
Unit & e2e tests	`references/testing.md`	Tests

Must do

Use Svelte 5 runes ($state, $props, $derived) in new components unless the repo is still Svelte 4.
Server-only secrets via $env/dynamic/private or $env/static/private — never PUBLIC_.
Same-origin API proxy in prod (Caddy /api → Axum) so the browser uses relative URLs.
Type loads/actions with generated ./$types.
After mutating cookies in an action, update event.locals before subsequent loads in the same request.

Must not do

Fetch the public internet from load with browser cookies intended only for first-party API without understanding credential rules.
Store access tokens in localStorage when httpOnly cookies are viable.
Disable CSRF protection without a written threat-model exception.
Ship adapter-auto to a raw VPS when adapter-node is the actual runtime.
Put DB credentials in client-visible modules under src/lib imported by client components.

Read the full file on GitHub · 74 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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 First seen · 74 lines · 93 tokens per session scan A 624a0624c6d0

Subscribe to this mod's changes

rc-sveltekit is a skill published in the GitHub repository rodolfochicone/rc-project (19 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 898 once invoked, about $0.0005 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 2026-08-30.

Claude Code Frontend LLM Vue and Svelte ai-agents developer-tools

nuxt4-patterns

Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.

majiang213/OpenClaw-MAS · 37 tokens

browser-extension-developer

Use this skill when developing or maintaining browser extension code in the browser/ directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

yamadashy/repomix · 43 tokens

ui-animation

Builds, reviews, and measures UI motion, including springs, gestures, scroll effects, and curve fitting from recordings. Use when asked to "add animation", "match this easing", "reverse engineer this motion", or find animation opportunities. For action semantics use product-design; for visual layout use ui-design.

mblode/agent-skills · 65 tokens

ui-design

Designs and builds React/Next/Tailwind UI and audits visual and interaction defects. Use when asked to "build a landing page", "extract our design system", "add dark mode", "make this responsive", "remove UI slop", or "audit this component". For product decisions use product-design; for browser measurements use…

mblode/agent-skills · 80 tokens

scaffold-nextjs

Scaffolds a Next.js turborepo with Blode UI, icons, Ultracite, workspace hooks, and GitHub/Vercel setup. Use when asked to "create a Next.js project", "bootstrap a turborepo", or "start a new web app". For a page in an existing app use ui-design; for a CLI use scaffold-cli.