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 avibebuilder/claude-prime --skill frontend-developmentgit clone --depth 1 https://github.com/avibebuilder/claude-primeWrote 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/avibebuilder/claude-prime/frontend-development)<a href="https://agentmods.dev/skills/avibebuilder/claude-prime/frontend-development"><img src="https://agentmods.dev/badge/skills/avibebuilder/claude-prime/frontend-development/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/avibebuilder/claude-prime/frontend-development"><img src="https://agentmods.dev/badge/skills/avibebuilder/claude-prime/frontend-development.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 | $0.00144 | $0.01167 |
| Opus 5.5 | $0.00058 | $0.00467 |
| Sonnet 5.5 | $0.00029 | $0.00233 |
| Haiku 4.5 | $0.00014 | $0.00117 |
Grade A, and why
frontend-development 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Development
Project-specific patterns for React/Next.js/TypeScript frontend work.
Architecture Decisions
Server-First Boundaries
Start with Server Components. Only add 'use client' when you need interactivity, state, or browser APIs. Extract only the interactive leaf — not the entire page or section.
Colocation Over Centralization
Types, hooks, and utilities that serve one feature live in that feature's directory. Only truly shared code goes in global directories.
Composition Over Customization
Compose existing components rather than adding props/variants. shadcn/ui components are meant to be copied and modified. Build up from primitives.
Data Flows Down, Events Flow Up
Server fetches data and passes it as props. Client components handle interactions and call server actions. Never fetch in client components what could be fetched on the server.
Gotchas
'use client'does NOT mean "runs only in the browser" — it runs on the server during SSR too. It means "include in the client bundle." Putting secrets or DB calls in a'use client'file will leak them.- Importing a Server Component into a Client Component makes it a Client Component. The boundary propagates DOWN. Pass server content as
childrenprops instead. useEffectwith empty deps fires AFTER paint — useuseLayoutEffectfor DOM measurements that affect layout, but never in Server Components.- Next.js
fetch()caches by default in App Router. Add{ cache: 'no-store' }orrevalidate: 0for data that must be fresh. Forgetting this causes stale data bugs that only appear in production. - Tailwind classes are purged at build time — dynamically constructed class names like
bg-${color}-500will be missing. Use complete class names or safelist them. keyprop on mapped elements must be stable and unique. Using array index as key causes subtle bugs when list items are reordered, inserted, or deleted.useSearchParams()requires a<Suspense>boundary in Next.js App Router or the entire page becomes client-rendered.- shadcn/ui components are source code, not a library. After
npx shadcn-ui add, the component lives in YOUR codebase — modify it directly, don't wrap it. - React Hook Form's
register()returns a ref — don't also pass your ownrefto the same input without merging them. asyncServer Components that throwredirect()ornotFound()must NOT be wrapped in try/catch — these work by throwing special errors that Next.js catches upstream.
What ships with it
16 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.
- references/biome.md 5.4 KB
- references/conventions.md 2.2 KB
- references/data-fetching/axios.md 2.0 KB
- references/data-fetching/overview.md 437 B
- references/data-fetching/tanstack.md 3.3 KB
- references/data-fetching/trpc-tanstack.md 2.0 KB
- references/nextjs/file-structure.md 2.2 KB
- references/nextjs/overview.md 348 B
- references/nextjs/patterns.md 2.2 KB
- references/react/file-structure.md 2.8 KB
- references/react/overview.md 436 B
- references/react/patterns.md 3.6 KB
- references/react/state.md 1.7 KB
- references/shadcn.md 2.0 KB
- references/tailwind.md 1.1 KB
- references/typescript.md 1.9 KB
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 · 77 lines · 144 tokens per session scan A 59424d348131
frontend-development is a skill published in the GitHub repository avibebuilder/claude-prime (120 stars, last pushed 5mo ago), licensed MIT. It adds 144 tokens to every session and 1,167 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
react-architect
React 19 standards — TypeScript strict, feature-based components, hooks-first composition, TanStack Query for server state, zustand for cross-tree client state, Suspense + ErrorBoundary at every async boundary, Radix for a11y. Use when writing or reviewing React components, hooks, or client-side state.
electron-dev
Electron desktop apps with React, TypeScript, and Vite. Use for IPC, window/tray, PTY terminals, WebRTC, and packaging.
react-component-generator
Generate React components with TypeScript, proper props, hooks, and accessibility. Use when creating new React components, UI elements, or refactoring existing components.
nextjs-react-redux-typescript-cursor-rules
Comprehensive Next.js, React, Redux, and TypeScript development guidelines covering SOLID principles, component architecture, and best practices.
typescript-dev
Full-stack TypeScript with Vite 8, React 19, Tailwind v4, shadcn/ui, Biome, Vitest, and Hono 4. Use when setting up or working in a TypeScript project - components, styling, build and HMR, tests, lint/CI, or a Hono API with type-safe RPC.
nextjs-react-typescript
Expert in TypeScript, Node.js, Next.js App Router, React, Shadcn UI, Radix UI and Tailwind.