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 | $0.00047 | $0.06400 |
| Opus 5.5 | $0.00019 | $0.02560 |
| Sonnet 5.5 | $0.00009 | $0.01280 |
| Haiku 4.5 | $0.00005 | $0.00640 |
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 14d 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 — 724 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.rolldownOptions.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, rolldownOptions.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 --> rolldownOptions.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.
- 14d ago Changed · +2 lines · +1 tokens per session 6b9db86bf85d
- 2mo 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 (107 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 6,400 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 2026-08-30.
Other agents, from other repositories
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
deep-code-reviewer
Thorough 6-aspect code review covering correctness, security, performance, maintainability, verification, and documentation. Use for comprehensive PR reviews or code quality audits.
phase-verifier
Fresh-context acceptance verifier dispatched by /implementation:implement-dispatch at phase boundaries and for post-phase source commits: checks a phase's binary acceptance criteria against the actual diff with the orchestrator's rationale withheld, and returns a per-criterion verdict grounded in direct evidence. Its…
compare-labeler
Read-only labeler for /docs-hygiene:compress compare: labels every difference between two versions of a skill directory and returns rows plus a VERDICT line. Dispatched by /docs-hygiene:compress; not intended for direct ad-hoc use.
dnp-performance-analyst
⚡ .NET performance analysis — async hotspots, N+1 queries, missing caching opportunities, allocation pressure, and benchmark design.
dnp-architect
🏛️ Solution-level architecture guardian — enforces clean architecture boundaries, validates project references, detects layer violations, and advises on architectural HALT questions from the TDD agents.