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.
npx agentmods add rules/nedcodes-ok/cursorrules-collection/nuxtgit clone --depth 1 https://github.com/nedcodes-ok/cursorrules-collectionWhat 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 | $0.00424 | $0.00424 |
| Opus 5 | $0.00212 | $0.00212 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
nuxt 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- nuxt — 100% identical, 0 lines differ
What it actually says
Nuxt 3 Cursor Rules
You are an expert Nuxt 3 developer. Follow these rules:
Architecture
- Auto-imports are on: dont manually import ref, computed, useState, useFetch
- File-based routing in pages/. Use definePageMeta for middleware/layout
- Server routes in server/api/ and server/routes/
- Composables in composables/ are auto-imported — use them liberally
Data Fetching
- useFetch for component-level data with SSR support
- useAsyncData with custom fetch logic when useFetch is too simple
- $fetch for client-only or server-side (event handlers, server routes)
- Always provide a unique key to useAsyncData to avoid hydration mismatches
- lazy: true for non-critical data, watch for reactive refetching
State
- useState for SSR-safe shared state (replaces Vuex for simple cases)
- Pinia for complex state management with devtools support
- Never use ref() for shared state — it wont survive SSR hydration
Server
- Server routes return data directly — Nuxt serializes automatically
- Use defineEventHandler for all server routes
- Validate input with getValidatedQuery/getValidatedBody + Zod
- H3 utilities: getHeader, setCookie, createError for server logic
- Throw createError({ statusCode: 404 }) — Nuxt shows error page
Performance
- NuxtImg for optimized images with provider support
- Route rules in nuxt.config for per-route caching/prerendering
- useNuxtData for accessing cached data from other composables
- Payload extraction for static sites — reduces JS bundle
Config
- Runtime config (runtimeConfig) for env vars — never process.env in client
- App config (app.config.ts) for build-time non-sensitive config
- Layers for sharing config/components across projects
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.
- yesterday First seen · 46 lines · 424 tokens per session scan A 5a7946ca4010
nuxt is a cursor rule published in the GitHub repository nedcodes-ok/cursorrules-collection (37 stars, last pushed 6mo ago), licensed MIT. It adds 424 tokens to every session, about $0.0021 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.