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.
git clone --depth 1 https://github.com/bradleybeatz1313/awesome-agents-mdWrote 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/rules/bradleybeatz1313/awesome-agents-md/cursorrules)<a href="https://agentmods.dev/rules/bradleybeatz1313/awesome-agents-md/cursorrules"><img src="https://agentmods.dev/badge/rules/bradleybeatz1313/awesome-agents-md/cursorrules/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/rules/bradleybeatz1313/awesome-agents-md/cursorrules"><img src="https://agentmods.dev/badge/rules/bradleybeatz1313/awesome-agents-md/cursorrules.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 | $0.00645 | $0.00645 |
| Opus 5.5 | $0.00258 | $0.00258 |
| Sonnet 5.5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
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 2mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor rules — Next.js 15 + React 19 + TypeScript + Tailwind 4
You are working in a Next.js 15 App Router project. See AGENTS.md for full conventions.
The five rules that matter most
- Default to Server Components. Only
"use client"when you genuinely need state, effects, browser APIs, or a client-only library. - Server Actions for mutations. Don't write API routes for first-party form submissions.
- Use
cn()from@/lib/utilsfor className composition. Never concatenate className strings manually. - No
any. Useunknownand narrow. Thetscconfig is strict — don't loosen it. - Named exports only. Default exports are reserved for Next's special files.
Stack details
- Package manager: pnpm
- Database: Drizzle ORM with PostgreSQL
- UI: shadcn components (don't edit
components/ui/*) - Forms: React Hook Form + Zod
- Tests: Vitest + Testing Library + Playwright
Imports
Use @/* path alias for everything below project root. Group imports:
- React/Next
- Third-party
@/lib/*,@/hooks/*@/components/*- Local relative
When you generate a new route
- Decide: marketing (public, in
app/(marketing)) or app (auth-gated, inapp/(app))? - If it fetches data, do it in the Server Component, not a
useEffectin a Client Component. - Wrap async children in
<Suspense fallback={<Skeleton />}>. - Add a
loading.tsxfor route-level loading state anderror.tsxfor errors.
When you add a component
- Server by default; add
"use client"only when proven necessary. - Props interface defined inline above the component.
- Forward
classNameand merge withcn(). - Forward
refonly when the component wraps a DOM element (useReact.forwardRefif needed; React 19 components often don't).
Tailwind 4 specifics
- Config is CSS-first in
app/globals.css— don't look fortailwind.config.ts. - Use design tokens (CSS variables defined in
globals.css) instead of hardcoded colors. - Prefer
flex/gridover absolute positioning unless overlay required.
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.
- 2mo ago First seen · 63 lines · 645 tokens per session scan A fdbfd30fbbee
cursorrules is a cursor rule published in the GitHub repository bradleybeatz1313/awesome-agents-md (2 stars, last pushed 6mo ago), licensed MIT. It adds 645 tokens to every session, about $0.0026 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 2026-08-31.
Other cursor rules, from other repositories
pyspark-etl-best-practices-cursorrules-prompt-file
Cursor rules for PySpark ETL development with code style, joins, window functions, map operations, and Iceberg patterns.
project-epic-template-cursorrules-prompt-file
Cursor rules for project development with epic template integration.
react-tanstack-router-query-cursorrules-prompt-file
Cursor rules for React SPAs combining TanStack Router v1 and TanStack Query v5 for zero-loading-spinner routing and type-safe server state.
ankra-cli
Ankra CLI rules and best practices for managing Kubernetes clusters via the Ankra platform.
playwright-integration-testing-cursorrules-prompt-file
Cursor rules for Playwright development with integration testing.
go-backend-scalability-cursorrules-prompt-file
Cursor rules for Go development with backend scalability.