A background Nuxt guide that helps choose the right Nuxt-specific guidance before using general Vue or module instructions. Nuxt is a framework for building Vue web applications.

Use it on Nuxt tasks to select the appropriate Nuxt pack or decide when Vue or module guidance is needed.

It prevents framework guidance from being applied at the wrong level when a Nuxt feature already defines the approach.

How onmax/nuxt-convex configures Codex

Reuse

Borrowing it

Nothing to install: this file belongs to onmax/nuxt-convex. 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/onmax/nuxt-convex/main/.codex/skills/nuxt/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/onmax/nuxt-convex

Made for: Codex.

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/skills/onmax/nuxt-convex/nuxt/github.svg)](https://agentmods.dev/skills/onmax/nuxt-convex/nuxt)

Your own site

<a href="https://agentmods.dev/skills/onmax/nuxt-convex/nuxt"><img src="https://agentmods.dev/badge/skills/onmax/nuxt-convex/nuxt/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/skills/onmax/nuxt-convex/nuxt"><img src="https://agentmods.dev/badge/skills/onmax/nuxt-convex/nuxt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,632 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	$0.00043	$0.02632
Opus 5.5	$0.00017	$0.01053
Sonnet 5.5	$0.00009	$0.00526
Haiku 4.5	$0.00004	$0.00263

Measured 22d ago against content hash 8ee8b926e0ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 22d 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.

.codex/skills/nuxt/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nuxt Skill Index

This file keeps the highest-frequency Nuxt decisions in context. Use it to avoid generic Vue fallbacks, then route into the right Nuxt pack, Vue guidance, or module delta skill.

Monorepo Scope

This skill applies only to the playground subtree of this monorepo. Treat files and tasks outside playground as out of scope unless the user explicitly redirects you there.

Activation Flow

Explore the project first: inspect the real page, component, route, server handler, collection, or module surface you are changing.
Use the routing sections in this file and load the smallest matching Nuxt pack.
If the remaining work is mainly Vue component, composable, reactivity, or SFC work, open Vue Best Practices.
If module authoring is part of the task, load Module Authoring Conventions before changing defineNuxtModule, runtime extensions, hooks, or release scaffolding.
If an installed module owns the problem, open its entry under references/modules.
Apply module guidance as delta-only rules inside that module's APIs, config, runtime behavior, and owned files.

High-Frequency Nuxt Decisions

If the task touches SSR, initial page load, or route-driven data, prefer useFetch or useAsyncData before onMounted plus $fetch.
If the task changes page options, layout selection, route middleware, or page-level behavior, check definePageMeta before adding ad hoc wiring.
If the task changes title, meta tags, canonical URLs, or OG data, check useHead or useSeoMeta before page-meta or template markup.
If content lives in JSON or YAML records, or the UI needs generated docs navigation, choose data collections and collection-navigation primitives before manual assembly.
If the UI surface is page chrome, a table, a form, a modal, a command palette, or a dropdown, prefer a Nuxt UI primitive before raw HTML or custom listeners.
If runtime config, tokens, secrets, or privileged API calls are involved, keep them server-side and expose only a server route or the minimum public config.
If hydration, browser-only APIs, time, randomness, or cookies are involved, use SSR-safe primitives first and isolate browser-only work behind ClientOnly or onMounted.
If the fix touches errors, fallback UI, or recovery flow, check both global and local surfaces before concluding the work is complete.
If the solution looks correct but uses generic Vue or hand-rolled HTML, confirm Nuxt, Nuxt Content, or Nuxt UI does not already own that abstraction.
If the task is module-specific, use the module entry and keep module guidance scoped; do not replace broad Nuxt rules with module-specific rules.

Read the full file on GitHub · 124 lines

Files

What ships with it

51 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

22d ago First seen · 124 lines · 43 tokens per session scan A 8ee8b926e0ca

Subscribe to this mod's changes

nuxt is a skill published in the GitHub repository onmax/nuxt-convex (21 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 2,632 once invoked, about $0.0002 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 2026-10-05.

Frontend Vue and Svelte

shadcn-svelte

Pre-built shadcn-svelte components for json-render Svelte apps. Use when working with @json-render/shadcn-svelte, adding standard UI components to a Svelte catalog, or building Svelte web UIs with shadcn-svelte + Tailwind CSS components.

vercel-labs/json-render · 63 tokens

add-localization

Adds or extends multilingual localization in a Power Pages code-site SPA. Use whenever the user asks to translate, localize, internationalize, support multiple languages, add a language selector, add locale routes, repair an i18n setup, or add languages to an existing React, Vue, Angular, or Astro Power Pages site.

microsoft/power-platform-skills · 69 tokens

nuxt-convex: Skill for Codex