frontend — React / Vite frontend (projx template)
> Stack-scoped notes. The root [`../CLAUDE.md`](../CLAUDE.md) carries cross-cutting standards — read both, they compose.
>
> This directory is a **projx template**: a working
methodology. This is 60%+ of the skill.]
## Guidelines
[ALWAYS/NEVER/CRITICAL rules]
```
## Quality Bar
Anthropic's `frontend-design` skill is the benchmark: ~60 lines, immediately actionable, uses NEVER/CRITICAL for guardrails, philosophy over
Pydantic AI that uses Vercel AI SDK and Elements. The project consists of a frontend (Vite + React + TypeScript) and a Python backend (FastAPI + Pydantic AI).
## Development Commands
**Frontend:**
```bash
server
# Testing
npm test # All tests
cd backend && npm test # Backend Jest tests
cd frontend && npm test # Frontend Vitest tests
# Building
npm run build # Build both packages
```
### Development Server Guidelines
Claude Code (claude.ai/code) when working with code in this repository.
## Project Overview
DeerFlow Frontend is a Next.js 16 web interface for an AI agent system. It communicates with
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.