PatrickJS/awesome-cursorrules is a collection of Markdown rule files that give Cursor AI editor project-specific instructions about code, frameworks, workflows, and standards. Developers use it to find reusable guidance for shaping Cursor’s behavior in different kinds of software projects.
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/patrickjs/awesome-cursorrules/react-formengine-ai-form-builder-cursorrules-prompt-filegit clone --depth 1 https://github.com/PatrickJS/awesome-cursorrulesWrote 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/patrickjs/awesome-cursorrules/react-formengine-ai-form-builder-cursorrules-prompt-file)<a href="https://agentmods.dev/rules/patrickjs/awesome-cursorrules/react-formengine-ai-form-builder-cursorrules-prompt-file"><img src="https://agentmods.dev/badge/rules/patrickjs/awesome-cursorrules/react-formengine-ai-form-builder-cursorrules-prompt-file.svg" alt="Measured on agentmods" 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 | $0.01681 | $0.01681 |
| Opus 5 | $0.00840 | $0.00840 |
| Sonnet 5 | $0.00336 | $0.00336 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
react-formengine-ai-form-builder-cursorrules-prompt-file 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 2d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FormEngine — AI Form Builder for React
Generate production-ready React forms from a screenshot, PDF, HTML, or text description. The output is a validated FormEngine JSON schema plus a runnable App.tsx — portable data, not throwaway JSX.
Default target: FormEngine Core (MIT, free) via @react-form-builder/core
@react-form-builder/components-rsuite(or Material UI / Mantine).
Source repo: https://github.com/lukinov/ai-form-builder
What you produce — every time
form.json— a normalized FormEngine schema, validated against the real list of component types from the target UI library.App.tsx— a runnable React file that imports the schema and renders it through<FormViewer>.- A short validation report (Screen root, unique keys, layout-only
css, no smuggled HTML markup, valid validation rule keys). - Install command + a link to the free Online FormBuilder (https://formbuilder.formengine.io) so the user can tweak visually.
Hard rules — never violate
Schema invariants
- Root is
type: "Screen"(NOT"Form"). - Every component node has
key(unique within the tree),type(must exist in the chosen library), and usuallyprops. - Every prop value is wrapped:
"label": { "value": "Email" }— never"label": "Email". - Validations live under
schema.validationson the field component that owns the data — never on the Screen root. - Use the correct tooltip/error types:
- RSuite:
RsTooltip/RsErrorMessage - MUI:
MuiTooltip/MuiErrorWrapper - Mantine:
MtTooltip/MtErrorWrapper
- RSuite:
Layout vs. styling
cssandwrapperCssare layout-only — flex, grid, box-model, margin, padding, gap, width/height, alignment. Never color, font, background, border, shadow, radius, opacity, transform.- Visual styling belongs in the UI library's theme provider in
App.tsx(<CustomProvider>/<ThemeProvider>/<MantineProvider>). - The legacy
stylefield is forbidden — usecss/wrapperCss. - The shape is
{ "any": { "object": { "<layout-key>": "<value>" } } }, never a plain CSS string. - No companion
.cssfile alongsideApp.tsx. No rootclassName. No<style>blocks. Nostyled-components.
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.
- 2d ago First seen · 165 lines · 1,681 tokens per session scan A ee1ddc866d8e
react-formengine-ai-form-builder-cursorrules-prompt-file is a cursor rule published in the GitHub repository PatrickJS/awesome-cursorrules (40,732 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 1,681 tokens to every session, about $0.0084 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 2026-09-03.
Other cursor rules, from other repositories
react
React and Next.js component conventions.
react-typescript-auto
This rule enforces best practices for building React 18+ applications with TypeScript, ensuring type safety, maintainability, and consistency.
react-component-hook-testing-auto
Enforces best practices for unit testing React components and custom hooks using React Testing Library and Vitest.
nextjs-react19-auto
This rule enforces Next.js best practices for React 19 with TypeScript.
react-19
React 19 patterns including new hooks, Server Components, and modern best practices.
Analyze-Data
Analyzes provided datasets, metrics, or structured data files (CSV, JSON, etc.) to identify trends, patterns, summaries, or answer specific questions about the data.