react-expert

react-expert is a skill for Claude Code, Codex from Aarvion-AI/stackwise-skills. It costs 134 tokens per session (2,266 once invoked), scanned A, original, MIT.

A development skill for React 19 and Next.js 15 applications, including pages, server and browser components, forms, data fetching, and tests. React is a JavaScript interface library, while Next.js adds routing and server features.

In plain words
What is it for?
Use it to add routes and layouts, build forms and mutations, fetch data, handle shared state, improve slow pages with streaming, and test components or server actions.
Why use it?
It helps keep server and browser code in the right places and avoids outdated patterns that can cause loading, rendering, or hydration problems.

Skill for Claude CodeCodex

Part of the stackwise plugin — 14 skills 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 skills/aarvion-ai/stackwise-skills/react-expert
Any agent
npx skills add Aarvion-AI/stackwise-skills --skill react-expert
Clone the repo
git clone --depth 1 https://github.com/Aarvion-AI/stackwise-skills

Made for: Claude Code, Codex.

Or install stackwise, the plugin that ships this one along with the rest of its 14 skills.

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/skills/aarvion-ai/stackwise-skills/react-expert.svg)](https://agentmods.dev/skills/aarvion-ai/stackwise-skills/react-expert)
Your own site
<a href="https://agentmods.dev/skills/aarvion-ai/stackwise-skills/react-expert"><img src="https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/react-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,266 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 $0.00134 $0.02266
Opus 5 $0.00067 $0.01133
Sonnet 5 $0.00027 $0.00453
Haiku 4.5 $0.00013 $0.00227

Measured 4d ago against content hash ba74665085a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

skills/react-expert/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React Expert

Turns Claude into a senior React 19 + Next.js 15 App Router engineer who defaults to Server Components, keeps client boundaries minimal, and never ships legacy patterns.

When to Use This Skill

  • Add or modify routes, layouts, and components in a Next.js 15 App Router project
  • Implement mutations with server actions, useActionState, and progressive-enhancement forms
  • Decide where the Server/Client Component boundary goes and fix boundary/hydration errors
  • Wire client-side data fetching with TanStack Query v5 (including SSR hydration)
  • Choose and implement state management (server state vs Zustand vs Context vs URL state)
  • Add Suspense boundaries and streaming to slow pages; fix waterfalls
  • Write or fix tests for components, hooks, and server actions in an RSC codebase

Core Workflow

  1. Analyze - Read package.json (confirm React 19 / Next 15, check for babel-plugin-react-compiler, @tanstack/react-query, zustand), next.config.ts, and the nearest layout.tsx/existing components to learn conventions. Identify whether the code you will touch runs on the server, the client, or both - this decides every pattern below.
  2. Design the boundary - Default to Server Components. Push "use client" to the smallest leaf that needs interactivity; pass Server Component output through as children/props rather than importing server code into client files. Fetch data on the server where possible; mutations go through server actions.
  3. Implement - TypeScript only, function components only, current APIs only: use() for promises/context in render, useActionState for action state, ref as a normal prop (no forwardRef), no manual useMemo/useCallback/memo when React Compiler is enabled. Load the matching reference file (table below) before writing unfamiliar patterns.
  4. Verify types/lint - run npx tsc --noEmit and npx next lint (or npx eslint . if the project migrated to the ESLint CLI); fix all reported issues and re-run until clean before proceeding.
  5. Test - run the project's test command (npx vitest run or npx jest); write or update tests for the change following references/testing.md; fix all failures and re-run until clean.
  6. Prove it works - run npx next build (catches server/client boundary violations, missing Suspense around useSearchParams, and dynamic API misuse that dev mode tolerates); fix all reported issues and re-run until clean. For behavior changes, start npx next dev and exercise the route.

Read the full file on GitHub · 146 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 First seen · 146 lines · 134 tokens per session scan A ba74665085a3

Subscribe to this mod's changes

react-expert is a skill published in the GitHub repository Aarvion-AI/stackwise-skills (5 stars, last pushed yesterday), licensed MIT. It adds 134 tokens to every session and 2,266 once invoked, about $0.0007 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.