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 agentmods add rules/barrosohub/frontend-stack-blueprint/cursorrulesgit clone --depth 1 https://github.com/barrosohub/frontend-stack-blueprintWhat 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 | $0.01746 | $0.01746 |
| Opus 5 | $0.00873 | $0.00873 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
cursorrules 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 yesterday.
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.
This is a copy
92% identical to frontend-stack-blueprint — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Stack Blueprint
⚠️ DEPRECATION: This
.cursorrulesfile is kept for backward compatibility. Cursor now reads from.cursor/rules(modern format). New projects should use.cursor/rulesinstead.Canonical frontend stack for any new project. Platform-agnostic. This file defines the technology decisions and rules an AI coding agent MUST follow when generating frontend code.
Stack
- TypeScript ≥7 (strict mode, no
any) - React ≥19.2.7 (function product components; class Error Boundaries allowed)
- TanStack Router ≥1 (default) or React Router ≥8
- pnpm (priority package manager) · Node.js >=22.22 · Bun ≥1 (runtime alternative)
- Vite ≥8 (requires Node.js >=22.22)
- Vitest ≥4 (4.x recommended) + Playwright ≥1.61 for deployed UI
- Protected CI merge gate + Husky + lint-staged + ESLint + Prettier
- Base UI · Radix/React Aria alternatives · shadcn/ui (recommended) · Floating UI · Embla · cmdk
- Tailwind CSS ≥4 + clsx + tailwind-merge (cn() utility required)
- Motion (formerly Framer Motion) —
import from 'motion/react' - DESIGN.md Design Contract (provisional, optional): root
DESIGN.md→ generated Tailwind 4 tokens - React Hook Form + Zod
- Data Access (optional): Prisma ≥7
- Authentication (optional): Better Auth ≥1
- Managed Services (optional): Neon Postgres | Cloudflare D1 | Cloudflare R2 | Cloudflare KV | Resend
- date-fns ≥4.1 (+@date-fns/tz)
- Zustand · TanStack Query ≥5 (TanStack Store remains under evaluation)
- Lexical (primary) · ProseMirror (fallback) · Shiki
- Advanced Capabilities (optional): Markdown · TanStack Table · Recharts · Mermaid · CodeMirror · xterm/node-pty · Yjs · PDF.js
- Format.js · react-intl
- Sentry · OpenTelemetry · Statsig (capability-gated)
- Lucide (default icon library)
Architecture (MANDATORY)
- Structure by feature/domain, NEVER by file type
- Composition over inheritance — hooks for logic reuse
- Strong typing: strict mode, no
any; explicit public boundaries and useful local inference - DRY: extract only after stable shared semantics are proven
- KISS: components ≤150 lines, functions ≤30 lines
- YAGNI: no speculative features or abstractions
- React Compiler 1.x: incremental opt-in after compatibility and performance validation
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.
- yesterday First seen · 147 lines · 1,746 tokens per session scan A a799ce202802
cursorrules is a cursor rule published in the GitHub repository barrosohub/frontend-stack-blueprint (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,746 tokens to every session, about $0.0087 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to frontend-stack-blueprint, differing in 11 lines, and is treated as a copy.
Other cursor rules, from other repositories
development-conventions
Development conventions, code style, and best practices for the Kaneo project.
test-running
When running tests, use the --watch false flag to avoid watch mode.
general
Wonder Blocks design system conventions, component patterns, and coding standards.
backend
Backend development rules for TT Studio - AI model management backend.
middleware-auth
Next.js middleware auth — prevents auth logic being placed in middleware instead of route handlers.
project-context
Core project context — tech stack, folder structure, and global conventions.