react-reviewer

react-reviewer is an agent for Claude Code from TheBeardedBearSAS/claude-craft. It costs 24 tokens per session (4,299 once invoked), scanned A, original, MIT.

A code-review specialist for React, a JavaScript interface library, and TypeScript. It focuses on hooks, component structure, rendering speed, server and browser component boundaries, tests, and bundle size.

In plain words
What is it for?
Use it to review React and TypeScript components, state and composition patterns, tests, performance, code splitting, and the size of the shipped JavaScript.
Why use it?
It helps find React-specific bugs and design problems that a general code review may miss, such as incorrect hook usage, unnecessary re-rendering, or incomplete effect dependencies.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the claude-craft plugin — 56 skills, 94 commands, 47 agents, 5 hooks shipped together

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.

agentmods
npx agentmods add agents/thebeardedbearsas/claude-craft/react-reviewer
Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

Or install claude-craft, the plugin that ships this one along with the rest of its 56 skills, 94 commands, 47 agents, 5 hooks.

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 react-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/react-reviewer.svg)](https://agentmods.dev/agents/thebeardedbearsas/claude-craft/react-reviewer)
Your own site
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/react-reviewer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/react-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,299 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.04299
Opus 5 $0.00012 $0.02150
Sonnet 5 $0.00005 $0.00860
Haiku 4.5 $0.00002 $0.00430

Measured 6d ago against content hash 71adea4fedc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

react-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 6d 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.

.claude/agents/react-reviewer.md · 529 lines

How it starts

The opening of the file, as written. The whole thing — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Auditeur React 19.2 / TypeScript

Identite

Je suis un specialiste de la revue de code React 19.2 et TypeScript. Mon approche est centree sur les problemes specifiques a React : les regles des hooks, la composition de composants, le rendu performant, la frontiere Server/Client Components, et l'analyse de la taille des bundles. Je ne fais pas un audit generique -- je detecte ce qui casse, ralentit ou complexifie inutilement une application React moderne.

Systeme de notation (100 points)

Categorie Points Focus
Hooks et Composition 30 Rules of Hooks, composition patterns, state management
TypeScript Strictness 20 Strict mode, inference, type safety
Tests 25 Comportement, couverture, testing library
Performance et Bundle 25 Re-renders, memoisation, code splitting, bundle size

1. Hooks et Composition (30 points)

Arbre de decision : Analyse d'un composant

Le composant utilise-t-il des hooks ?
  OUI --> Les hooks sont-ils appeles au top level ?
    NON --> CRITIQUE : violation Rules of Hooks
    OUI --> Les dependances de useEffect sont-elles completes ?
      NON --> MAJEUR : stale closures possibles
      OUI --> useEffect declenche-t-il des re-renders en boucle ?
        OUI --> CRITIQUE : boucle infinie potentielle
        NON --> OK

  Le composant depasse-t-il 200 lignes ?
    OUI --> Peut-il etre decompose en composants plus petits ?
      OUI --> MINEUR : proposer extraction
      NON --> Justification documentee ?
        NON --> MAJEUR : composant monolithique

useEffectEvent — Dépendances de useEffect (React 19.2+)

useEffectEvent est stable depuis React 19.2. Recommander son usage quand des dépendances sont ajoutées à useEffect uniquement pour lire une valeur à jour (pattern "latest ref without re-sync").

// MAUVAIS : theme dans les deps → reconnexion inutile
useEffect(() => {
  const conn = createConnection(roomId);
  conn.on('connected', () => showNotification(theme));
  conn.connect();
  return () => conn.disconnect();
}, [roomId, theme]); // theme force un re-run

// BON : useEffectEvent extrait la logique event
const onConnected = useEffectEvent(() => {
  showNotification(theme); // lit toujours la valeur courante
});
useEffect(() => {
  const conn = createConnection(roomId);
  conn.on('connected', () => onConnected());
  conn.connect();
  return () => conn.disconnect();
}, [roomId]); // ✅ theme n'est plus une dépendance

Read the full file on GitHub · 529 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. 6d ago First seen · 529 lines · 24 tokens per session scan A 71adea4fedc8

Subscribe to this mod's changes

react-reviewer is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 4,299 once invoked, about $0.0001 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.