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/gabrielmoreira/agent-skills-mirrorWrote 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/gabrielmoreira/agent-skills-mirror/frontend)<a href="https://agentmods.dev/rules/gabrielmoreira/agent-skills-mirror/frontend"><img src="https://agentmods.dev/badge/rules/gabrielmoreira/agent-skills-mirror/frontend.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 | $0.00000 | $0.00550 |
| Opus 5 | $0.00000 | $0.00275 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
frontend 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 7d 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 an expert in TypeScript, Node.js, Vite, Vue.js, Vue Router, Pinia, VueUse, Ant Design Vue, and UnoCSS, with a deep understanding of best practices and performance optimization techniques in these technologies.
Package manager: Bun
-
bun run typecheck Code Style and Structure - Write concise, maintainable, and technically accurate TypeScript code with relevant examples. - Use functional and declarative programming patterns; avoid classes. - Favor iteration and modularization to adhere to DRY principles and avoid code duplication. - Use descriptive variable names with auxiliary verbs (e.g., isLoading, hasError). - Organize files systematically: each file should contain only related content, such as exported components, subcomponents, helpers, static content, and types.
- Define API and types in app/src/api Naming Conventions
- In src/components, the name should be CamelCase (e.g., app/src/components/ChatGPT/ChatGPT.vue) - In src/views, the folder name should be lower case with underline, but the component name should be CamelCase (e.g., app/src/views/system/About.vue) - Favor named exports for functions. TypeScript Usage - Use TypeScript for all code; prefer interfaces over types for their extendability and ability to merge. Syntax and Formatting - Use the "function" keyword for pure functions to benefit from hoisting and clarity. - Always use the Vue Composition API script setup style.
- Use Vue3.4+ features like defineModel(), useTemplateRef(), v-bind Same-name Shorthand UI and Styling - Use Ant Design Vue, UnoCSS for components and styling. - Implement responsive design with UnoCSS and Antdv Flex layout; use a mobile-first approach. Performance Optimization - Leverage VueUse functions where applicable to enhance reactivity and performance. - Wrap asynchronous components in Suspense with a fallback UI. - Use dynamic loading for non-critical components. - Optimize images: use WebP format, include size data, implement lazy loading. - Implement an optimized chunking strategy during the Vite build process, such as code splitting, to generate smaller bundle sizes. Key Conventions - Optimize Web Vitals (LCP, CLS, FID) using tools like Lighthouse or WebPageTest.
Comments
- Always response in English
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.
- 7d ago First seen · 48 lines · 0 tokens per session scan A 1685eed5b69d
frontend is a cursor rule published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 550 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
tailwind-v4
Standards for Tailwind CSS v4 usage in Svelte files.
javascript-astro-tailwind-css-cursorrules-prompt-f
Cursor rules for JavaScript development with Astro and Tailwind CSS integration.
coding-best-practices
Cursor rule "coding-best-practices" from hexianWeb/Third-Person-MC, covering coding best practices and user interface (ui).
component-styles-folder
When a Vue feature needs a separate SCSS/CSS file (for example to satisfy SFC line limits), styles live only under that feature's styles/ subfolder — never beside the .vue at the feature root.
vue-bem-scss
BEM class names and scoped SCSS in Vue single-file components.
tailwind-patterns
Tailwind CSS patterns and best practices for Vue 3.