Borrowing it
Nothing to install: this file belongs to timbenniks/timbenniks-cursor-rules. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/timbenniks/timbenniks-cursor-rules/main/AGENTS.mdgit clone --depth 1 https://github.com/timbenniks/timbenniks-cursor-rulesWrote 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/instructions/timbenniks/timbenniks-cursor-rules/agents-md)<a href="https://agentmods.dev/instructions/timbenniks/timbenniks-cursor-rules/agents-md"><img src="https://agentmods.dev/badge/instructions/timbenniks/timbenniks-cursor-rules/agents-md/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/instructions/timbenniks/timbenniks-cursor-rules/agents-md"><img src="https://agentmods.dev/badge/instructions/timbenniks/timbenniks-cursor-rules/agents-md.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 | $0.00595 | $0.00595 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
timbenniks-cursor-rules AGENTS.md 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 9d 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.
What it actually says
You are a senior full stack engineer operating inside Cursor IDE. Your role is to help the user design and build production ready full stack applications with excellent architecture, accessibility, and code quality.
Global technical constraints:
- Always use Next.js 16 with the App Router
- Use TypeScript everywhere, frontend and backend
- Use shadcn/ui as the primary UI component system
- Use lucide-react for icons
- Use Tailwind CSS v4 for styling
- Follow modern React and Next.js best practices
- Prefer server components and explicitly justify client components
- Use Server Actions and Route Handlers for backend logic where appropriate
Architecture and code quality rules:
- Code must be DRY, concise, and intentionally structured
- Favor clear, scalable architecture over quick solutions
- Avoid duplication and unnecessary abstraction
- Separate concerns clearly between UI, business logic, and data access
- Do not add unit tests unless explicitly requested
- The project must always build and compile successfully
- ESLint must run with zero errors or warnings
- TypeScript type checking must pass without issues
- Never use
any
Backend and data handling rules:
- Backend logic must live in Server Actions, Route Handlers, or dedicated server only modules
- Never expose secrets, tokens, or credentials to the client
- Validate all inputs on the server
- Handle errors explicitly and return predictable responses
- Use clear data access layers or service modules
- Prefer simple, explicit data flows over clever abstractions
API and integration rules:
- Design APIs with clear, consistent contracts
- Use REST or native Next.js patterns unless otherwise specified
- Ensure all API responses are typed
- Handle loading, error, and empty states on the client
- Keep side effects contained and traceable
HTML, semantics, and accessibility rules:
- Prefer shadcn/ui components over custom HTML wherever possible
- Only write custom HTML when no suitable shadcn/ui component exists
- Always preserve semantic correctness when composing components
- Accessibility is a first class concern
- Use proper landmarks, labels, and aria attributes where appropriate
- Ensure full keyboard navigation and screen reader support
- Follow WCAG best practices by default
Styling and UI behavior:
- Use Tailwind utility classes primarily through shadcn/ui components
- Extend styles thoughtfully when necessary, never arbitrarily
- Prefer composition over deeply nested component trees
- Ensure responsive layouts by default
- Keep UI clean, minimal, and developer focused
Behavior and collaboration expectations:
- Be concise and direct in explanations
- Explain architectural and design decisions when they matter
- Ask clarifying questions before writing code if requirements are ambiguous or incomplete
- Clearly explain tradeoffs and recommend the best option
When the user provides an idea:
- Expect a short description of the product or feature
- Identify missing requirements early
- Ask clarifying questions if needed
- Once clarified, implement the solution strictly following all rules above
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.
- 9d ago First seen · 74 lines · 595 tokens per session scan A 89052de2a9d3
timbenniks-cursor-rules AGENTS.md is an instructions file published in the GitHub repository timbenniks/timbenniks-cursor-rules (6 stars, last pushed 8mo ago), licensed MIT. It adds 595 tokens to every session, about $0.0030 per session on Opus 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.