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/jalcantarab/v0-vibecodexWrote 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/jalcantarab/v0-vibecodex/ai-development)<a href="https://agentmods.dev/rules/jalcantarab/v0-vibecodex/ai-development"><img src="https://agentmods.dev/badge/rules/jalcantarab/v0-vibecodex/ai-development.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 | $0.01593 | $0.01593 |
| Opus 5 | $0.00796 | $0.00796 |
| Sonnet 5 | $0.00319 | $0.00319 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
ai-development 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.
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Assisted Development Guidelines
AI Tool Integration
1. Supported AI Tools
- v0.dev: React component generation
- Bolt.new: Full-stack development environment
- Lovable: AI-assisted application building
- Replit: Collaborative coding platform
2. Prompt Structure
When creating prompts for AI tools, follow this structure:
// Tool-specific prompt template
const prompt = {
content: "Create a [component/feature] that [specific requirements]",
tooltips: [
{
text: "key concept",
explanation: "Explanation for beginners",
highlightColor: "bg-yellow-100"
}
]
}
3. Component Patterns for AI
// AI-friendly component structure
interface ComponentProps {
// Clear, descriptive prop names
title: string
description?: string
variant?: 'default' | 'outline' | 'ghost'
size?: 'sm' | 'md' | 'lg'
}
export function ComponentName({
title,
description,
variant = 'default',
size = 'md',
...props
}: ComponentProps) {
// Clear, well-documented logic
const variantClasses = {
default: 'bg-primary text-primary-foreground',
outline: 'border border-input bg-background',
ghost: 'hover:bg-accent hover:text-accent-foreground'
}
return (
<div
className={cn(
'base-classes',
variantClasses[variant],
sizeClasses[size],
props.className
)}
{...props}
>
{/* Clear, semantic structure */}
</div>
)
}
Code Documentation for AI
1. Component Comments
/**
* ComponentName - Brief description
*
* Features:
* - Feature 1: Description
* - Feature 2: Description
*
* Usage:
* <ComponentName title="Example" variant="outline" />
*
* AI Notes:
* - This component follows the [pattern] for consistency
* - Uses [specific library] for [specific functionality]
* - Designed for [specific use case]
*/
2. Function Documentation
/**
* FunctionName - Clear description of what it does
*
* @param param1 - Description of parameter
* @param param2 - Description of parameter
* @returns Description of return value
*
* Example:
* const result = functionName('example', { key: 'value' })
*
* AI Context:
* - This function is used for [specific purpose]
* - Follows [specific pattern] for consistency
* - Handles [specific edge cases]
*/
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 · 283 lines · 1,593 tokens per session scan A ef2dfa40752e
ai-development is a cursor rule published in the GitHub repository jalcantarab/v0-vibecodex (8 stars, last pushed 1y ago), licensed MIT. It adds 1,593 tokens to every session, about $0.0080 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 cursor rules, from other repositories
co-dialectic
Co-Dialectic prompt sharpening and verification rules for Cursor.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
prompting-for-qe
Soạn/tinh chỉnh prompt cho tác vụ QE (sinh test case, phân tích requirement, tóm tắt tài liệu test, phân tích log) — đặc biệt khi output AI lan man, chung chung, bịa, hoặc muốn chốt prompt thành template tái dùng.
llm-zod-jsonschema
Best Practice for LLM Output Parsing with Zod and JSON Schema.
react
React best practices and patterns for modern web applications.
prompt-evals
Prompt eval fixtures — case design, assertions, versioning, CI gates, no PII in golden data.