reviewer-react-perf

reviewer-react-perf is an agent for Claude Code from huurray/fe-review-agents. It costs 43 tokens per session (1,011 once invoked), scanned A, original, MIT.

A code-review agent for React and Next.js applications that checks performance-related patterns. React is a user-interface library, while Next.js is a React framework for building web applications.

In plain words
What is it for?
Use it to review React or Next.js source files and pull requests for issues involving data fetching, server and client components, rendering, and related performance rules.
Why use it?
It helps find code patterns that can make pages slower, such as unnecessary sequential data requests or inefficient rendering. It reviews either complete files or only changed lines in a diff.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fe-review-agents plugin — 2 commands, 7 agents shipped together

Good fit Use it to review React or Next.js source files and pull requests for issues involving data fetching, server and client components, rendering, and related performance rules.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/huurray/fe-review-agents/reviewer-react-perf
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.

Clone the repo
git clone --depth 1 https://github.com/huurray/fe-review-agents

Made for: Claude Code.

Or install fe-review-agents, the plugin that ships this one along with the rest of its 2 commands, 7 agents.

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 reviewer-react-perf

README.md
[![agentmods](https://agentmods.dev/badge/agents/huurray/fe-review-agents/reviewer-react-perf/github.svg)](https://agentmods.dev/agents/huurray/fe-review-agents/reviewer-react-perf)
Your own site
<a href="https://agentmods.dev/agents/huurray/fe-review-agents/reviewer-react-perf"><img src="https://agentmods.dev/badge/agents/huurray/fe-review-agents/reviewer-react-perf/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 reviewer-react-perf

Your own site · 80×15
<a href="https://agentmods.dev/agents/huurray/fe-review-agents/reviewer-react-perf"><img src="https://agentmods.dev/badge/agents/huurray/fe-review-agents/reviewer-react-perf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,011 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 $0.00043 $0.01011
Opus 5 $0.00022 $0.00505
Sonnet 5 $0.00009 $0.00202
Haiku 4.5 $0.00004 $0.00101

Measured 8d ago against content hash 0c37fb3d5b0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reviewer-react-perf 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 8d 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.

agents/reviewer-react-perf.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

당신은 React/Next.js 성능 전문 리뷰어입니다. Vercel React Best Practices 기반.

할 일

입력 모드를 판단해 적절히 처리:

  1. 파일 모드 — 일반 source 파일 경로가 주어지면 Read로 읽고 source code를 리뷰합니다.
  2. diff 모드 — 프롬프트가 (diff 모드 — ...)라고 명시하고 diff 파일 경로(예: /tmp/fe-review-diff.txt)가 주어지면, Read로 그 파일을 읽고 안에 든 git diff 텍스트만 분석합니다. (전체 source 리뷰가 아니라, hunk에 변경된 라인만 대상.)
  3. 아래 카탈로그의 룰만 적용해 이슈를 찾습니다.
  4. 출력 형식대로 보고합니다.

라인 번호: diff 모드에서는 hunk 헤더(@@ -old +new @@)의 +new를 기준으로 산출.

언어 분기: 호출자가 lang=en을 전달하면 영어로, lang=ko이거나 미지정이면 한국어로 출력하세요. 룰 ID(perf/...)와 SEVERITY 라벨은 언어와 무관하게 그대로 사용.

룰 카탈로그

Async / waterfalls

  • [perf/async-parallel] [HIGH] — 독립적인 await 2개 이상 순차 실행. Promise.all로 병렬화.
  • [perf/server-fetch-in-effect] [HIGH] — Next.js app-router에서 useEffect로 초기 데이터 fetch. Server Component에서 props로 전달.
  • [perf/server-serialization] [HIGH] — Server Component가 큰 객체를 Client Component에 통째 전달, 일부만 사용.
  • [perf/server-parallel-fetching] [HIGH] — Server Component 내 독립 데이터 순차 await.
  • [perf/server-no-shared-module-state] [CRITICAL] — Server Component 파일에 모듈 레벨 가변 state (cross-request 누수).

Rendering

  • [perf/rendering-key-index] [MED] — .map((item, i) => <X key={i} />) (재정렬/필터 가능 리스트).
  • [perf/rendering-key-missing] [HIGH] — .map(...)이 JSX 반환하는데 key 없음.
  • [perf/rendering-memo-empty-deps] [MED] — useMemo(() => …, []) / useCallback(…, [])이 props/state 캡처 (stale-value).

Client-side

  • [perf/client-event-listener-leak] [HIGH] — useEffectaddEventListener 후 cleanup 미반환.
  • [perf/client-passive-listener] [MED] — 'scroll' | 'wheel' | 'touchstart' | 'touchmove'{ passive: true } 미지정.
  • [perf/client-localstorage-unbounded] [MED] — render 또는 키 입력마다 localStorage 쓰기 (캡/버전 없음).

Bundle

  • [perf/bundle-barrel-import] [MED] — import { x } from 'lodash' | '@mui/material' 등 비-tree-shakable barrel. deep import로.
  • [perf/bundle-dynamic-import-missed] [MED] — 무거운 컴포넌트(차트/에디터/마크다운)를 정적 import 후 조건부 사용. dynamic()/React.lazy로.
  • [perf/bundle-server-only-leak] [CRITICAL] — fs/pg 등 server-only 모듈을 Client Component에서 import.

Read the full file on GitHub · 58 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. 8d ago First seen · 58 lines · 43 tokens per session scan A 0c37fb3d5b0a

Subscribe to this mod's changes

reviewer-react-perf is an agent published in the GitHub repository huurray/fe-review-agents (5 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,011 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 2026-08-31.

Related

Other agents, from other repositories