vite-mcp-next

vite-mcp-next is a skill for Claude Code, Codex from xiaou66/vite-plugin-vue-mcp-next. It costs 45 tokens per session (1,078 once invoked), scanned A, original, MIT.

A debugging guide for running Vite and Vue web pages. Vite is a tool for developing web applications, while Vue is a framework for building their user interfaces; the guide connects to the running page to inspect its actual state.

In plain words
What is it for?
It is for inspecting page structure, screenshots, console logs, network requests, Vue components, routing, and Pinia state while debugging a local Vite and Vue application.
Why use it?
It helps diagnose problems that source code alone may not reveal, such as browser errors, incorrect page elements, failed requests, or unexpected application state.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for inspecting page structure, screenshots, console logs, network requests, Vue components, routing, and Pinia state while debugging a local Vite and Vue application.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xiaou66/vite-plugin-vue-mcp-next/vite-mcp-next
Install

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.

Any agent
npx skills add xiaou66/vite-plugin-vue-mcp-next --skill vite-mcp-next
Clone the repo
git clone --depth 1 https://github.com/xiaou66/vite-plugin-vue-mcp-next

Made for: Claude Code, 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.

agentmods badge for vite-mcp-next

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaou66/vite-plugin-vue-mcp-next/vite-mcp-next/github.svg)](https://agentmods.dev/skills/xiaou66/vite-plugin-vue-mcp-next/vite-mcp-next)
Your own site
<a href="https://agentmods.dev/skills/xiaou66/vite-plugin-vue-mcp-next/vite-mcp-next"><img src="https://agentmods.dev/badge/skills/xiaou66/vite-plugin-vue-mcp-next/vite-mcp-next/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 vite-mcp-next

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiaou66/vite-plugin-vue-mcp-next/vite-mcp-next"><img src="https://agentmods.dev/badge/skills/xiaou66/vite-plugin-vue-mcp-next/vite-mcp-next.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,078 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01078
Opus 5 $0.00023 $0.00539
Sonnet 5 $0.00009 $0.00216
Haiku 4.5 $0.00005 $0.00108

Measured 11d ago against content hash 0ed5d324bab3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vite-mcp-next 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 11d 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.

skills/vite-mcp-next/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vite-mcp-next

Overview

vite-mcp-next exposes local Vite + Vue runtime state through MCP. Use it before guessing from source code when the task asks to inspect a running page, verify UI, debug browser errors, trace requests, or inspect Vue app state.

When to Use

  • User asks to inspect, open, verify, screenshot, or debug a local Vite/Vue page
  • The answer depends on actual browser DOM, Console, Network, Vue component state, Router, or Pinia
  • You need evidence from the running app before changing code
  • You need to compare source expectations with runtime behavior

Do not use it for static code-only questions where reading files is enough.

Quick Reference

Need Tool
Find available pages and targets list_pages
Inspect a copied element ID get_element_context
Refresh the current page reload_page
Inspect DOM structure get_dom_tree
Find elements by selector query_dom
Capture visual evidence take_screenshot
Read browser logs get_console_logs
Inspect one runtime console object argument inspect_console_arg
Reset old browser logs clear_console_logs
Inspect requests get_network_requests
Inspect one request deeply get_network_request_detail
Reset old request records clear_network_requests
Inspect browser storage list_storage, get_storage_item
Mutate browser storage set_storage_item, delete_storage_item, clear_storage
Inspect Vue component tree get_component_tree
Inspect one component state get_component_state
Edit runtime component state edit_component_state
Highlight a component highlight_component
Inspect Vue Router get_router_info
Inspect Pinia stores get_pinia_tree, get_pinia_state
Evaluate page expression evaluate_script

Tool Order

  1. Call list_pages first. Confirm the page, runtime connection, and any cdp:* target.
  2. If the user provides an elementId such as src/App.vue:12:8, call get_element_context before editing source.
  3. For layout or content questions, call get_dom_tree or query_dom.
  4. For visual verification, call take_screenshot and report whether source is cdp or snapdom.
  5. For browser errors, call get_console_logs; if a runtime Hook log contains an object argument with argId, call inspect_console_arg only when that object detail is needed.
  6. For API behavior, call get_network_requests, then get_network_request_detail for the relevant id.
  7. For storage questions, call list_storage first, then get_storage_item, set_storage_item, delete_storage_item, or clear_storage for the selected scope.
  8. For Vue-specific behavior, call get_component_tree, get_component_state, get_router_info, get_pinia_tree, or get_pinia_state.

Read the full file on GitHub · 80 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. 11d ago First seen · 80 lines · 45 tokens per session scan A 0ed5d324bab3

Subscribe to this mod's changes

vite-mcp-next is a skill published in the GitHub repository xiaou66/vite-plugin-vue-mcp-next (19 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 1,078 once invoked, about $0.0002 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.