What is ai-tools CLAUDE.md?

A project-specific instruction file for developing a Svelte application and Model Context Protocol server. It documents setup, environment variables, commands, testing, and database tasks.

It helps install dependencies, configure the Voyage API key for embeddings, run or build the app, check and format code, test it, and manage database migrations.

It gives an AI coding agent the repository rules and commands needed to work on the project without guessing its development process.

How sveltejs/ai-tools configures Claude Code

About the project

Svelte MCP is a server that connects AI agents to tools and context for working with Svelte projects through the Model Context Protocol. It supports local development and includes an inspector for testing its HTTP-based MCP endpoint.

sveltejs/ai-tools · 335 stars · on GitHub · mcp.svelte.dev

Reuse

Borrowing it

Nothing to install: this file belongs to sveltejs/ai-tools. 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/sveltejs/ai-tools/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sveltejs/ai-tools

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/instructions/sveltejs/ai-tools/claude-md/github.svg)](https://agentmods.dev/instructions/sveltejs/ai-tools/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sveltejs/ai-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/sveltejs/ai-tools/claude-md/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/instructions/sveltejs/ai-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/sveltejs/ai-tools/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 922 This file is loaded in full into every session.

When invoked 922 The same file — it is already loaded in full.

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	$0.00922	$0.00922
Opus 5.5	$0.00369	$0.00369
Sonnet 5.5	$0.00184	$0.00184
Haiku 4.5	$0.00092	$0.00092

Measured 8d ago against content hash 364d9287c7fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-tools CLAUDE.md 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 8d 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.

CLAUDE.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Commands

This is a Svelte MCP (Model Context Protocol) server implementation that includes both SvelteKit web interface and MCP server functionality.

Setup

pnpm i
cp .env.example .env
# Set the VOYAGE_API_KEY for embeddings support in .env
pnpm dev

Common Commands

pnpm dev - Start SvelteKit development server
pnpm build - Build the application for production
pnpm start - Run the MCP server (Node.js entry point)
pnpm check - Run Svelte type checking
pnpm check:watch - Run type checking in watch mode
pnpm lint - Run prettier check and eslint
pnpm format - Format code with prettier
pnpm test - Run unit tests with vitest
pnpm test:watch - Run tests in watch mode

Database Commands (Drizzle ORM)

pnpm db:push - Push schema changes to database
pnpm db:generate - Generate migration files
pnpm db:migrate - Run migrations
pnpm db:studio - Open Drizzle Studio

Architecture

MCP Server Implementation

The core MCP server is implemented in src/lib/mcp/index.ts using the tmcp library with:

Transport Layers: Both HTTP (HttpTransport) and STDIO (StdioTransport) support
Schema Validation: Uses Valibot with ValibotJsonSchemaAdapter
Main Tool: svelte-autofixer - analyzes Svelte code and provides suggestions/fixes

Code Analysis Engine

Located in src/lib/server/analyze/:

Parser (parse.ts): Uses svelte-eslint-parser and TypeScript parser to analyze Svelte components
Scope Analysis: Tracks variables, references, and scopes across the AST
Rune Detection: Identifies Svelte 5 runes ($state, $effect, $derived, etc.)

Autofixer System

Autofixers (src/lib/mcp/autofixers.ts): Visitor pattern implementations for code analysis
Walker Utility (src/lib/index.ts): Enhanced AST walking with visitor mixing capabilities
Current Autofixer: assign_in_effect - detects assignments to $state variables inside $effect blocks

Read the full file on GitHub · 101 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.

8d ago Changed 364d9287c7fd
1mo ago First seen · 101 lines · 922 tokens per session scan A 1707a6375458

Subscribe to this mod's changes

ai-tools CLAUDE.md is an instructions file published in the GitHub repository sveltejs/ai-tools (335 stars, last pushed today), licensed MIT. It adds 922 tokens to every session, about $0.0037 per session on Opus 5.5. 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.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

ai-tools: Instructions file for Claude Code