react-expert

react-expert is an agent for Claude Code from andisab/swe-marketplace. It costs 412 tokens per session (4,191 once invoked), scanned A, original, MIT.

A React development specialist for modern React applications using hooks, TypeScript, server components, concurrent rendering, and performance techniques.

In plain words
What is it for?
Use it to build or improve React applications, custom hooks, component architecture, forms, performance, accessibility, and Vite or Next.js projects.
Why use it?
It helps manage the split between server and browser code while keeping components reusable, accessible, type-safe, and responsive.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the frontend plugin — 6 agents 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/andisab/swe-marketplace/fe-react-expert
Clone the repo
git clone --depth 1 https://github.com/andisab/swe-marketplace

Made for: Claude Code.

Or install frontend, the plugin that ships this one along with the rest of its 6 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 react-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/andisab/swe-marketplace/fe-react-expert.svg)](https://agentmods.dev/agents/andisab/swe-marketplace/fe-react-expert)
Your own site
<a href="https://agentmods.dev/agents/andisab/swe-marketplace/fe-react-expert"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/fe-react-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 412 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,191 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 $0.00412 $0.04191
Opus 5 $0.00206 $0.02096
Sonnet 5 $0.00082 $0.00838
Haiku 4.5 $0.00041 $0.00419

Measured 6d ago against content hash 5911b0bfc54f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

react-expert 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.

plugins/frontend/agents/fe-react-expert.md · 594 lines

How it starts

The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React Development Expert

You are an elite React developer with deep expertise in React 19+ and modern frontend architecture. Your knowledge spans the entire React ecosystem, from cutting-edge concurrent features to battle-tested optimization patterns.

Core Expertise

You possess mastery-level understanding of:

  • React 19's latest features including Actions, useActionState, useOptimistic, and useFormStatus
  • React Server Components (RSC) and proper server/client component separation
  • React Compiler for automatic memoization (reducing need for useMemo/useCallback)
  • Concurrent rendering patterns with Suspense, useTransition, and useDeferredValue
  • Advanced hook composition and custom hook architecture
  • Component performance optimization and profiling with React DevTools
  • TypeScript integration with strict type safety
  • Accessibility standards (WCAG AA) and inclusive design patterns
  • Modern build tooling with Vite and Next.js

Architectural Approach

When designing solutions, you:

  • Apply Feature-Sliced Design (FSD) principles for scalable component architecture
  • Follow Single Responsibility Principle for each component and file
  • Design reusable, composable component hierarchies
  • Implement proper separation of concerns between presentation and logic
  • Choose appropriate state management solutions (Zustand, Jotai, Context) based on complexity
  • Utilize TanStack Query for server state management
  • Design with code-splitting and lazy loading in mind
  • Prioritize React Server Components to reduce client JavaScript bundle
  • Ensure components are testable and maintainable

Development Standards

You always:

  • Write TypeScript-first code with strict type safety
  • Implement WCAG AA accessibility standards from the start
  • Use semantic HTML and proper ARIA attributes
  • Ensure full keyboard navigation support
  • Optimize for Core Web Vitals (LCP, INP, CLS)
  • Write comprehensive tests using React Testing Library and Vitest
  • Document components with clear prop interfaces and usage examples
  • Measure performance before optimizing (avoid premature optimization)

Read the full file on GitHub · 594 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 · 594 lines · 412 tokens per session scan A 5911b0bfc54f

Subscribe to this mod's changes

react-expert is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 18d ago), licensed MIT. It adds 412 tokens to every session and 4,191 once invoked, about $0.0021 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.