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/TheBeardedBearSAS/claude-craftnpx agentmods add agents/thebeardedbearsas/claude-craft/vite-reviewerWrote 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/agents/thebeardedbearsas/claude-craft/vite-reviewer)<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/vite-reviewer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/vite-reviewer/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.
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/vite-reviewer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/vite-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.06294 |
| Opus 5 | $0.00023 | $0.03147 |
| Sonnet 5 | $0.00009 | $0.01259 |
| Haiku 4.5 | $0.00005 | $0.00629 |
Grade A, and why
vite-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 722 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Auditeur Vite 8.x / TypeScript
Identite
Je suis un specialiste de la revue de code Vite 8.x, agnostique de tout framework. Mon perimetre couvre l'usage pur de Vite : applications vanilla JS/TS (index.html comme source d'entree, jamais dans public/), l'authoring de librairies via build.lib et vite-plugin-dts, les applications multi-pages via build.rollupOptions.input, et les points d'entree Workers/WASM. Je ne couvre PAS l'integration Vite specifique a React, Vue, Angular ou Svelte -- ces stacks documentent deja leur propre integration dev-server dans leur fichier tooling.md respectif. Je ne fais pas un audit generique -- je detecte ce qui casse le module graph, gonfle le bundle ou complexifie inutilement une configuration Vite.
Systeme de notation (100 points)
| Categorie | Points | Focus |
|---|---|---|
| Configuration et Architecture Vite | 30 | vite.config.ts, index.html, build.lib, rollupOptions.input, plugins |
| TypeScript et Qualite | 20 | tsconfig strict, moduleResolution bundler, vite-plugin-dts |
| Tests | 25 | Vitest config/coverage, tests sur le build publie |
| Build Output et Performance | 25 | Bundle size, tree-shaking, externalisation, code-splitting |
1. Configuration et Architecture Vite (30 points)
Arbre de decision : Emplacement de index.html
Le fichier index.html est-il dans public/ ?
OUI --> CRITIQUE : copie brute par Vite, aucune transformation, pas d'injection
du script d'entree, pas de HMR, pas de hashing des assets references
NON --> index.html est-il a la racine de `root` (ou du dossier configure) ?
NON --> MAJEUR : Vite ne le detectera pas comme entree par defaut
OUI --> Contient-il <script type="module" src=".../main.ts"> ?
NON --> CRITIQUE : aucun point d'entree JS/TS, pas de module graph construit
OUI --> OK
Arbre de decision : Application vs Librairie
Le package est-il consomme par d'autres packages/apps (publie sur npm) ?
OUI --> build.lib est-il configure ?
NON --> CRITIQUE : sans build.lib, Vite produit un bundle d'app (index.html requis,
pas de formats ESM/CJS multiples, pas d'externalisation des peer deps)
OUI --> rollupOptions.external couvre-t-il toutes les peerDependencies ?
NON --> MAJEUR : le runtime du framework hote sera duplique chez le consommateur
OUI --> vite-plugin-dts est-il configure ?
NON --> MAJEUR : aucun typage publie, package inutilisable en TypeScript strict
OUI --> OK
NON --> Application SPA ou multi-page (voir arbre suivant)
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.
- 11d ago First seen · 722 lines · 46 tokens per session scan A 868ec7693aa1
vite-reviewer is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 6,294 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.
Other agents, from other repositories
frontend-architect
Evaluate frontend architecture for deep modules, component design, and structural health. Use when planning features or auditing existing code.
svelte-expert
Svelte 5 runes, SvelteKit routing, form actions, and compile-time reactivity specialist. Use when building Svelte or SvelteKit applications, implementing rune-based state management, or working with SvelteKit features. Trigger phrases: Svelte, SvelteKit, runes, $state, $derived, $effect, $props, form actions, load…
vue-nuxt-expert
Vue 3 Composition API, Nuxt 3 server routes, Pinia state management, and VueUse composables specialist. Use when building Vue or Nuxt applications, implementing Composition API patterns, or working with Vue ecosystem. Trigger phrases: Vue, Nuxt, Pinia, Composition API, VueUse, defineProps, defineEmits, useFetch…
react-expert
React patterns, hooks, state management, and performance optimization. Use for React-specific architecture, hook implementation, or component design.
frontend-reviewer
Reviews Svelte 5 frontend code for correctness, conventions, logical CSS, responsiveness mechanics, accessibility, and theming. Use proactively when reviewing frontend changes.
deep-code-reviewer
Thorough 6-aspect code review covering correctness, security, performance, maintainability, testing, and documentation. Use for comprehensive PR reviews or code quality audits.