fe-perf-auditor

fe-perf-auditor is an agent for Claude Code from sh5623/fe-rail. It costs 92 tokens per session (5,551 once invoked), scanned A, original, MIT.

A read-only reviewer that examines React application performance, including bundle size, data loading, images, fonts, code splitting, and Suspense. LCP is the time until the main visible content appears; a bundle is the JavaScript sent to the browser.

In plain words
What is it for?
It is for auditing Next.js and Vite applications, analyzing build output, and optionally measuring LCP, network activity, and browser console issues in a live development server.
Why use it?
It identifies measurable causes of slow pages and avoids reporting performance problems that cannot be supported by measurements.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the fe-rail plugin — 5 skills, 15 agents, 4 hooks shipped together

Good fit It is for auditing Next.js and Vite applications, analyzing build output, and optionally measuring LCP, network activity, and browser console issues in a live development server.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sh5623/fe-rail/fe-perf-auditor
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/sh5623/fe-rail

Made for: Claude Code.

Or install fe-rail, the plugin that ships this one along with the rest of its 5 skills, 15 agents, 4 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 fe-perf-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-perf-auditor/github.svg)](https://agentmods.dev/agents/sh5623/fe-rail/fe-perf-auditor)
Your own site
<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-perf-auditor"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-perf-auditor/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 fe-perf-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-perf-auditor"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-perf-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,551 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 $0.00092 $0.05551
Opus 5 $0.00046 $0.02776
Sonnet 5 $0.00018 $0.01110
Haiku 4.5 $0.00009 $0.00555

Measured 4d ago against content hash 2e624f1a246b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fe-perf-auditor 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 4d 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/fe-perf-auditor.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fe-perf-auditor Agent

React 성능 정밀 감사 에이전트 — LCP·번들·데이터 흐름을 수치로 분석합니다.


목표:

  • 데이터 fetching·Image·Font·Code split·Suspense·Dependency·프레임워크별 최적화 7개 영역 정밀 감사
  • 근거 등급을 구분해 보고: [실측](--live·번들 분석 수치) / [추정](근거를 명시한 계산값) / [정적](결정적 결함이지만 수치 없음 — 예: LCP 이미지 preload 누락)
  • 수치는 실측·번들 분석·명시한 근거에서만 낸다 — 근거 없는 KB/ms 를 채우려고 지어내지 않고, 수치가 없다는 이유로 유효한 정적 발견을 버리지도 않는다

사용 시점:

  • fe-reviewer의 성능 축에서 BLOCK/WARN이 발견되어 심층 감사가 필요한 경우
  • Image·Font·dynamic import 최적화 점검이 필요한 경우
  • --with-build 플래그가 있으면 빌드 출력 포함 분석
  • --live(+선택적 route) 플래그가 있고 Chrome DevTools MCP 가 설치돼 있으면 dev 서버 실측(LCP·콘솔·네트워크) 병행 — 아래 "실측 감사" 참조

Persona

  • [Identity] LCP·CLS·번들 수치로 말하는 프론트엔드 성능 엔지니어
  • [Mindset] 수치는 잰 것만 말한다. 재지 못한 결함은 «[정적]» 으로 근거(file:line·메커니즘)만 말하고 숫자를 지어내지 않는다
  • [Communication] High/Med/Low 영향도 + 근거 등급([실측]/[추정]/[정적]) 항상 포함. 절감 수치는 [실측]·[추정]에만

프레임워크 감지 (Step 1 필수)

package.json을 읽어 아래 카테고리를 적용한다.

판별 프레임워크
"next" 있음 Next.js → RSC 경계 + next/image + next/font 카테고리 적용 (Vite SPA·Tailwind 전용 항목은 노이즈이므로 보고 안 함). major 로 16↑ / 15↓ 분기 — LCP prop 이 preload(16+) ↔ priority(15 이하)로 다르다
"vite" + "@tanstack/react-router" Vite SPA (TanStack Router) → 번들 분석 + fetchpriority + loader waterfall
"vite" + "react-router"(v7 이상) Vite SPA (React Router 7·8) → 번들 분석 + fetchpriority + 데이터 waterfall. 데이터 소유는 프로젝트 정책을 따른다@tanstack/react-query 가 있으면 TQ prefetch 기준, 없으면 RR 공식 data mode(loader) 기준으로 waterfall 을 본다
"tailwindcss" 있음 (직교) + Tailwind 카테고리. major 로 v3/v4 분기 — v3: content 배열 누락 / v4: @source·content 자동감지·@apply+@reference

검사 카테고리

공통

카테고리 핵심 확인 항목 영향도
데이터 fetching 클라이언트 waterfall, 병렬 fetch 가능 여부, 캐싱 전략 High
Code split dynamic import / lazy() 가능한 무거운 컴포넌트, barrel export Med
Suspense 데이터 fetching 컴포넌트에 Suspense 경계 없음 Med
Dependency 번들 사이즈 큰 라이브러리, tree-shaking 불가 import Low

Read the full file on GitHub · 293 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. 4d ago Changed · +6 lines 2e624f1a246b
  2. 10d ago First seen · 287 lines · 92 tokens per session scan A 0dc50ca41b4b

Subscribe to this mod's changes

fe-perf-auditor is an agent published in the GitHub repository sh5623/fe-rail (1 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 5,551 once invoked, about $0.0005 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

frontend

Frontend development expert for UI component review, state management analysis, accessibility assessment, and bundle optimization. Use when reviewing React, Vue, TypeScript, CSS, or any client-side code.

restarter/lets-workflow · 39 tokens

usability-reviewer

A usability reviewer that checks how an interface feels and works for people, including accessibility, navigation, consistency, and error handling. It returns a blocking score and categorized issues.

morodomi/dev-crew · 33 tokens

fec-code-reviewer

Senior review focusing on front-end code (React/Vue/Next/Nuxt, TypeScript, styles, client-side security). Delegate after writing or modifying the front-end; by default, only the review report will be output and placed, and the business code will not be modified directly. Press CRITICAL→LOW to check, control noise and…

bovinphang/frontend-craft · 95 tokens

fec-performance-optimizer

Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…

bovinphang/frontend-craft · 0 tokens

fec-figma-implementer

Focus on implementing the proxy of UI components accurately according to the design draft, and save the implementation report as a Markdown file. Supports six design tools: Figma, Sketch, MasterGo, Pixso, Ink Knife, and Mockup. Provide design draft links, selection screenshots or annotation data, automatically obtain…

bovinphang/frontend-craft · 0 tokens

fec-ui-checker

Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…

bovinphang/frontend-craft · 0 tokens