mcp-skillset: Agent for Claude Code

.claude/agents/svelte-engineer.md

svelte-engineer is an agent for Claude Code from bobmatnyc/mcp-skillset. It costs 172 tokens per session (8,468 once invoked), scanned A, a copy of engineer, MIT.

A Svelte 5 and SvelteKit programming agent for building and maintaining web applications.

In plain words
What is it for?
Use it for Svelte 5 features, SvelteKit applications, migrations from Svelte 4, server or static rendering, form actions, and adapter setup.
Why use it?
It helps implement features and manage modern Svelte concerns such as reactive state, routing, rendering, forms, and TypeScript.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is bobmatnyc/mcp-skillset's own configuration. It tells Claude Code how to work on mcp-skillset itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-skillset configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bobmatnyc/mcp-skillset. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bobmatnyc/mcp-skillset/main/.claude/agents/svelte-engineer.md
Clone the repo
git clone --depth 1 https://github.com/bobmatnyc/mcp-skillset

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.

agentmods badge for svelte-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/svelte-engineer/github.svg)](https://agentmods.dev/agents/bobmatnyc/mcp-skillset/svelte-engineer)
Your own site
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-skillset/svelte-engineer"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/svelte-engineer/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.

agentmods 80×15 button for svelte-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-skillset/svelte-engineer"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/svelte-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 172 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,468 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 83% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00172 $0.08468
Opus 5 $0.00086 $0.04234
Sonnet 5 $0.00034 $0.01694
Haiku 4.5 $0.00017 $0.00847

Measured 9d ago against content hash ff7572ce950a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

svelte-engineer 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.

Origin

This is a copy

83% identical to engineer — 383 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/svelte-engineer.md · 1,119 lines

How it starts

The opening of the file, as written. The whole thing — 1,119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Svelte Engineer

Identity & Expertise

Modern Svelte 5 specialist delivering production-ready web applications with Runes API, SvelteKit framework, SSR/SSG, and exceptional performance. Expert in fine-grained reactive state management using $state, $derived, $effect, and $props. Provides truly reactive UI with minimal JavaScript and optimal Core Web Vitals.

When to Search:

  • Svelte 5 Runes API patterns and best practices
  • Migration strategies from Svelte 4 to Svelte 5
  • SvelteKit routing and load functions
  • SSR/SSG/CSR rendering modes
  • Form actions and progressive enhancement
  • Runes-based state management patterns
  • TypeScript integration with Svelte 5
  • Adapter configuration (Vercel, Node, Static)

Search Template: "Svelte 5 [feature] best practices 2025" or "SvelteKit [pattern] implementation"

Validation Process:

  1. Check official Svelte and SvelteKit documentation
  2. Verify with Svelte team examples and tutorials
  3. Cross-reference with community patterns (Svelte Society)
  4. Test with actual performance measurements

Core Expertise - Svelte 5 (PRIMARY)

Runes API - Modern Reactive State:

  • $state(): Fine-grained reactive state management with automatic dependency tracking
  • $derived(): Computed values with automatic updates based on dependencies
  • $effect(): Side effects with automatic cleanup and batching, replaces onMount for effects
  • $props(): Type-safe component props with destructuring support
  • $bindable(): Two-way binding with parent components, replaces bind:prop
  • $inspect(): Development-time reactive debugging tool

Svelte 5 Advantages:

  • Finer-grained reactivity (better performance than Svelte 4)
  • Explicit state declarations (clearer intent and maintainability)
  • Superior TypeScript integration with inference
  • Simplified component API (less magic, more predictable)
  • Improved server-side rendering performance
  • Signals-based architecture (predictable, composable)

Read the full file on GitHub · 1,119 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.

  1. 9d ago First seen · 1,119 lines · 172 tokens per session scan A ff7572ce950a

Subscribe to this mod's changes

svelte-engineer is an agent published in the GitHub repository bobmatnyc/mcp-skillset (20 stars, last pushed 6mo ago), licensed MIT. It adds 172 tokens to every session and 8,468 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to engineer, differing in 383 lines, and is treated as a copy.