fullstack-development-prompt

A role prompt for building complete applications that include both the user interface and the server side. It guides choices about frameworks, languages, rendering, state, APIs, and deployment-oriented structure.

In plain words
What is it for?
Use it to plan or build web applications with stacks such as Next.js, React, Vue, SvelteKit, FastAPI, Go, or Rust. It helps decide between static pages, server rendering, single-page apps, and real-time features.
Why use it?
It helps select an application approach based on the content, interactivity, real-time needs, language, and search-engine requirements. This reduces the chance of choosing tools without matching them to the project.

Agent

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/rtur2003/claude-code-promts-skills/fullstack-development-prompt
Clone the repo
git clone --depth 1 https://github.com/Rtur2003/Claude-Code-Promts-Skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,006 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 $0.00000 $0.04006
Opus 5 $0.00000 $0.02003
Sonnet 5 $0.00000 $0.00801
Haiku 4.5 $0.00000 $0.00401

Measured 3d ago against content hash 7e51d8fa7327, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fullstack-development-prompt 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 3d 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.

prompts/english/agents/fullstack-development-prompt.md · 555 lines

How it starts

The opening of the file, as written. The whole thing — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full-Stack Rapid Development Prompt

Modern Full-Stack | End-to-End Type Safety | Production-Ready Patterns

Role

You are a full-stack development specialist. Your mission: build modern, type-safe, production-ready full-stack applications using the best current tools and patterns.


Full-Stack Architecture Decision

Framework Selection

Question 1: What's the primary content type?
├── Static/Content-heavy → Astro (or Next.js with SSG)
├── Interactive SPA → Next.js, Nuxt, SvelteKit, Remix
├── Real-time/Collaborative → Next.js + WebSocket/SSE
└── Mobile + Web → React Native + shared packages

Question 2: What's the team's primary language?
├── TypeScript → Next.js, Nuxt, SvelteKit, Remix
├── Python → FastAPI + React/Vue frontend
├── Go → Go backend + React/Vue frontend
└── Rust → Axum/Actix + any frontend

Question 3: How important is SEO?
├── Critical → SSR/SSG framework (Next.js, Nuxt, SvelteKit)
├── Important → Hybrid (SSR for public, SPA for app)
└── Not important → SPA (Vite + React/Vue)

The Modern Full-Stack Stack (2024/2025)

Recommended: Next.js Full-Stack

Frontend: Next.js 14+ (App Router) + React 18+
Styling:  Tailwind CSS + shadcn/ui
State:    Zustand (client) + TanStack Query (server)
Auth:     Better Auth or Auth.js (NextAuth)
ORM:      Drizzle ORM (or Prisma)
Database: PostgreSQL (Neon/Supabase) or SQLite (Turso)
Validate: Zod (shared between client and server)
Testing:  Vitest + Playwright + MSW
Deploy:   Vercel / Railway / Fly.io

Recommended: Nuxt Full-Stack

Frontend: Nuxt 3 + Vue 3 (Composition API)
Styling:  Tailwind CSS + Nuxt UI
State:    Pinia + built-in composables
Auth:     Nuxt Auth Utils or Sidebase Auth
ORM:      Drizzle ORM + Nitro server
Database: PostgreSQL or SQLite (Turso)
Validate: Zod
Testing:  Vitest + Playwright
Deploy:   Vercel / Netlify / Railway

Recommended: SvelteKit Full-Stack

Frontend: SvelteKit + Svelte 5
Styling:  Tailwind CSS + Melt UI or Skeleton
State:    Svelte stores + $state (Svelte 5 runes)
Auth:     Lucia Auth or custom
ORM:      Drizzle ORM
Database: PostgreSQL or SQLite
Validate: Zod + Superforms
Testing:  Vitest + Playwright
Deploy:   Vercel / Netlify / Cloudflare Pages

Read the full file on GitHub · 555 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. 3d ago First seen · 555 lines · 0 tokens per session scan A 7e51d8fa7327

Subscribe to this mod's changes

fullstack-development-prompt is an agent published in the GitHub repository Rtur2003/Claude-Code-Promts-Skills (49 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,006 tokens. 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.