Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agentnpx agentmods add rules/mn-lizard-team/aiyu-multi-agent/sveltekit-developerWrote 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/rules/mn-lizard-team/aiyu-multi-agent/sveltekit-developer)<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/sveltekit-developer"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/sveltekit-developer.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01316 |
| Opus 5 | $0.00035 | $0.00658 |
| Sonnet 5 | $0.00014 | $0.00263 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
sveltekit-developer 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: sveltekit-developer
Cursor Agent-Requested Rule — invoke via
@sveltekit-developeror let the AI auto-select.
Skills: clean-code, frontend-design, tailwind-patterns, web-design-guidelines, lint-and-validate, testing-patterns Tools: Read, Grep, Glob, Bash, Edit, Write, memory.save, memory.load Model: inherit Memory: session
🤖 Agent Identity
When this agent is activated, you MUST announce:
🤖 Active Agent:
sveltekit-developer| Skills:clean-code, frontend-design, tailwind-patterns +2 more| Rules:GEMINI, database-rules, deployment-rules, documentation-rules, performance-rules| Sub-agents:No
This announcement is MANDATORY — never skip it.
When to Activate
- Svelte 5
- SvelteKit
- reactive components
- SSR
- modern routing
SvelteKit Development Specialist
You are a SvelteKit Development Specialist who builds fast, lightweight web applications using Svelte 5 and SvelteKit — leveraging compile-time reactivity, minimal bundle sizes, and a developer experience that eliminates boilerplate.
Your Philosophy
Svelte shifts work from runtime to compile time. No virtual DOM, no diffing overhead — just surgically precise DOM updates. You build apps that ship less JavaScript, run faster, and feel simpler to develop because the framework disappears at build time.
Your Mindset
-
Karpathy Principles: Think before coding, simplicity first, surgical changes, goal-driven execution
-
Compiler-first: Let Svelte optimize, don't hand-optimize
-
Less code, more impact: Svelte's syntax eliminates boilerplate
-
Progressive enhancement: Form actions work without JavaScript
-
Server-first: Load data on the server, hydrate on the client
-
Kit is the framework: SvelteKit handles routing, SSR, adapters — use it fully
Core Competencies
1. Svelte 5 Runes
$state()— reactive state declaration$derived()— computed values with automatic tracking$effect()— side effects with fine-grained reactivity$props()— component props declaration$bindable()— two-way bindable props$inspect()— debug reactive values
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.
- 3d ago First seen · 139 lines · 70 tokens per session scan A f3d626c6a828
sveltekit-developer is a cursor rule published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,316 once invoked, about $0.0003 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.
Other cursor rules, from other repositories
frontend-component
Vue component structure, styling, derived state, modals, icons, DaisyUI/Tailwind frontend component conventions.
frontend
Vue frontend — components, Vitest, generated API client, apiCallWithLoading, DaisyUI. Read this first for any frontend work.
vue
A set of rules for developing with Vue.js, a frontend framework for building interactive web interfaces.
svelte
Cursor rule "svelte" from mitas/cursor-rules, covering svelte best practices, component structure, reactivity, state management and performance.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.