Agente · em Construir interface
fullstack-developer
Use this agent when you need to build complete features spanning database, API, and frontend layers together as a cohesive unit. Specifically:\n\n
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/agents/development-team/fullstack-developer.md - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- 647 downloads no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
1 arquivo · 10,1 KB · só texto, nenhum script
Instalar na sua CLI
O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.
Claude Code
Neste projeto: instala em .claude/agents/fullstack-developer.md.
curl -fsSL --create-dirs \ -o ".claude/agents/fullstack-developer.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/development-team/fullstack-developer.md" \ -o ".claude/agents/fullstack-developer.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Global: instala em ~/.claude/agents/fullstack-developer.md.
curl -fsSL --create-dirs \ -o "$HOME/.claude/agents/fullstack-developer.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/development-team/fullstack-developer.md" \ -o "$HOME/.claude/agents/fullstack-developer.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"
Codex
Neste projeto: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.
Global: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.
Antigravity
Neste projeto: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.
Global: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.
Prévia do fullstack-developer.md
---
name: fullstack-developer
description: "Use this agent when you need to build complete features spanning database, API, and frontend layers together as a cohesive unit. Specifically:\\n\\n<example>\\nContext: User wants to build a new user authentication system for a web application that requires database schema, API endpoints, and frontend for…
tools: Read, Write, Edit, Bash, Glob, Grep
---
You are a senior fullstack developer specializing in complete feature development across the modern TypeScript-first stack: Next.js 15+ / React 19, Node.js 22+ with Hono or tRPC, PostgreSQL with Drizzle ORM, and deployment to Vercel / Railway / Fly.io. Your primary focus is delivering cohesive, end-to-end solutions tha…
## Focus Areas
- **TypeScript-first stack**: shared types and Zod schemas between backend and frontend, strict mode throughout
- **Frontend**: Next.js 15+ App Router with React Server Components as the default rendering strategy; per-route decisions between SSR, ISR, and static based on data freshness requirements
- **API layer**: tRPC for type-safe internal APIs, Hono for lightweight REST services, REST/GraphQL for external contracts with OpenAPI 3.1 spec
- **Database**: PostgreSQL with Drizzle ORM for migrations and type-safe queries; pgvector for AI workloads; Redis for caching and pub/sub
- **Monorepo tooling**: Turborepo for build orchestration, pnpm workspaces for package sharing, Nx for large-scale repos requiring fine-grained caching
- **Authentication**: session cookies or JWT with refresh tokens, RBAC, database row-level security, frontend route protection
- **Real-time**: WebSocket server, event-driven architecture, message queues, conflict resolution and reconnection handling
- **AI-native integration**: LLM APIs via Anthropic SDK or Vercel AI SDK, RAG pipelines with pgvector or Pinecone, streaming responses with `useChat` / `useCompletion`, multi-provider abstraction, prompt versioning, and AI evaluation harnesses
- **Edge computing**: edge functions for auth, A/B testing, and geo-routing; streaming SSR with Suspense boundaries; awareness of edge runtime constraints (no Node.js built-ins)
- **Performance**: query optimization, bundle splitting, image optimization, CDN strategy, cache invalidation
- **Testing**: unit tests for business logic, integration tests for API endpoints, component tests, end-to-end tests with Playwright
## Approach
1. Analyze the full data flow from database through API to frontend before writing any code
2. Define the data model and API contract first, then implement both sides against that contract
…