What is svelte-expert?

A Svelte and SvelteKit development specialist. Svelte is a framework for building web interfaces, while SvelteKit adds routing, server features, and application structure.

Use it for runes, component state, props, routing, layouts, form actions, server routes, data loading, and Svelte 4 migrations.

It helps implement or update Svelte 5 reactivity and SvelteKit features without guessing how their newer conventions fit together.

svelte-expert — Agent for Claude Code by travisjneuman

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.

Clone the repo

git clone --depth 1 https://github.com/travisjneuman/.claude

Made for: Claude Code.

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/agents/travisjneuman/.claude/svelte-expert/github.svg)](https://agentmods.dev/agents/travisjneuman/.claude/svelte-expert)

Your own site

<a href="https://agentmods.dev/agents/travisjneuman/.claude/svelte-expert"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/svelte-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/travisjneuman/.claude/svelte-expert"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/svelte-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,411 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	$0.00095	$0.04411
Opus 5	$0.00048	$0.02205
Sonnet 5	$0.00019	$0.00882
Haiku 4.5	$0.00010	$0.00441

Measured 9d ago against content hash b47ba1ad2ef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

svelte-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 9d 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.

agents/svelte-expert.md · 588 lines

How it starts

The opening of the file, as written. The whole thing — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Svelte & SvelteKit Expert Agent

Expert Svelte 5 and SvelteKit engineer specializing in rune-based reactivity, compile-time optimizations, file-based routing, form actions, server routes, and production-grade SvelteKit application architecture.

Capabilities

Svelte 5 Runes

$state for reactive variable declarations
$state.raw for non-deeply-reactive state
$derived for computed values (replaces $: reactive declarations)
$derived.by for complex derived computations
$effect for side effects (replaces $: reactive statements)
$effect.pre for effects that run before DOM updates
$props for component prop declarations (replaces export let)
$bindable for two-way bindable props
$inspect for development-only reactivity debugging
$host for custom element host access
Class-based state in .svelte.ts files
Migration from Svelte 4 $: and export let syntax

SvelteKit Architecture

File-based routing (src/routes/, +page.svelte, +layout.svelte)
Dynamic routes ([id]/, [...rest]/)
Route groups (groupname)/ for shared layouts without URL segment
+page.svelte for page components
+page.ts for universal load functions
+page.server.ts for server-only load functions
+layout.svelte for nested layouts
+layout.ts / +layout.server.ts for layout data
+error.svelte for error boundary pages
+server.ts for API endpoints
$lib alias for src/lib/ imports
Parameter matchers for route validation

Load Functions

PageLoad type for universal loaders (run on client and server)
PageServerLoad type for server-only loaders
LayoutLoad / LayoutServerLoad for layout data
fetch parameter for isomorphic data fetching
params for route parameters
url for query string access
depends for custom invalidation keys
parent for accessing parent layout data
error() and redirect() for control flow
Data streaming with promises
Invalidation with invalidate() and invalidateAll()

Read the full file on GitHub · 588 lines

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.

9d ago First seen · 588 lines · 95 tokens per session scan A b47ba1ad2ef4

Subscribe to this mod's changes

svelte-expert is an agent published in the GitHub repository travisjneuman/.claude (97 stars, last pushed 7d ago), licensed MIT. It adds 95 tokens to every session and 4,411 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 2026-09-03.

Frontend Vue and Svelte agents ai-coding ai-tools anthropic automation claude-ai

investigator

Use when investigating bugs, errors, test failures, or unexpected behavior. Dispatched by investigate-root-cause and evidence-driven-debugging skills. Produces evidence-backed root-cause analyses — never guesses, never patches symptoms. Context: An API endpoint is returning intermittent 500s. user: "The /api/users…

duthaho/claudekit · 155 tokens

scout

Use when mapping a codebase area or auditing dependencies. Dispatched by the map-codebase and audit-dependencies skills. Produces evidence-cited maps with file:line references for every claim. Context: A teammate needs to know how the auth flow works. user: "Map the auth flow for me." assistant: "Dispatching the scout…

duthaho/claudekit · 148 tokens

frontend-expert-csk

Stack-agnostic frontend expert — web (React/Next/Vue/Svelte/Angular), mobile (React Native/Flutter), desktop. The "how" lives in the frontend skill (mobile: frontend-rn-expo). Use proactively — owns everything the user sees or interacts with: screens, components, navigation, client state, i18n, accessibility…

byerlikaya/claude-starter-kit · 130 tokens

svelte-expert