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.
npx skills add Cypsy1714/cchad --skill react-patterns-skillgit clone --depth 1 https://github.com/Cypsy1714/cchadWrote 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.
[](https://agentmods.dev/skills/cypsy1714/cchad/react-patterns-skill)<a href="https://agentmods.dev/skills/cypsy1714/cchad/react-patterns-skill"><img src="https://agentmods.dev/badge/skills/cypsy1714/cchad/react-patterns-skill/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.
<a href="https://agentmods.dev/skills/cypsy1714/cchad/react-patterns-skill"><img src="https://agentmods.dev/badge/skills/cypsy1714/cchad/react-patterns-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.00308 |
| Opus 5.5 | $0.00010 | $0.00123 |
| Sonnet 5.5 | $0.00005 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
react-patterns 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 1mo 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.
What it actually says
React patterns
Guidance for writing React that stays readable as it grows.
Components
- Keep components small and single-purpose. If a component does two things, split it.
- Prefer composition (passing children / render props) over configuration via a growing list of boolean props.
- Derive state during render instead of storing values you can compute.
Hooks
- Every
useEffectneeds a clear reason to exist. If it only transforms props into state, you probably don't need it — compute the value inline. - List every dependency an effect reads. Don't silence the linter; fix the dependency.
- Extract reused stateful logic into a custom
useXhook rather than copying effect bodies between components.
State
- Keep state as local as possible; lift it only when two components truly share it.
- Model server data with a data-fetching library (React Query / SWR) instead of
hand-rolled
useEffect+useStateloading flags. - Keep a single source of truth. Don't mirror the same value in two states.
Rendering
- Give lists stable
keys tied to identity, never the array index. - Reach for
useMemo/useCallbackonly when you have a measured performance problem, not by default.
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.
- 1mo ago First seen · 36 lines · 25 tokens per session scan A 4446e94580c6
react-patterns is a skill published in the GitHub repository Cypsy1714/cchad (1 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 308 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
prism-component
Implement a reusable, accessible, typed component from a design spec. Use when asked to "create a component", "build a widget", "implement this design", or "reusable UI element".
react-expert
Use when working in a React 19 / Next.js 15 codebase - .tsx/.jsx files, next.config.ts, app/ router directories, "use client"/"use server" directives, package.json with react or next dependencies. Builds and refactors Server/Client Components, server actions and forms, Suspense/streaming UIs, and TanStack Query or…
remix-expert
Use when working in a React Router 7 / Remix v2 framework-mode codebase with app/routes, loaders and actions, react-router.config.ts, useLoaderData / useActionData, Form, useNavigation, Outlet, or ErrorBoundary. Builds and refactors route modules, server data loading, mutations, pending UI, nested routing, and…
senior-frontend
Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
nextjs-ssr-patterns
Default command for population on a fresh worktree or after a git pull that includes a lockfile change: npm ci — lockfile-respecting, deterministic install. Run from the project root. This is the form CI workflows and Dockerfiles use. The bare npm install form is acceptable only when the lockfile is known-stale or for…