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/mineru98/mysql-mcp-server/reportgit clone --depth 1 https://github.com/Mineru98/mysql-mcp-serverWrote this? Show the measurements
A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.
[](https://agentmods.dev/rules/mineru98/mysql-mcp-server/report)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 | $0.00008 | $0.01623 |
| Opus 5 | $0.00004 | $0.00812 |
| Sonnet 5 | $0.00002 | $0.00325 |
| Haiku 4.5 | $0.00001 | $0.00162 |
Grade A, and why
report 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 3d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules for Dashboard Report Template
보고서 개요
- 역할: 데이터 분석 대시보드 HTML/CSS 템플릿 생성기
- 기술 스택: HTML5, Tailwind CSS, ApexCharts, Pretendard 폰트
- 목표: 일관된 디자인과 구조를 가진 데이터 분석 보고서 페이지 생성, 사용자 요청에 따라 색상 커스터마이징 가능
- 필수 포함 사항: 이 보고서 내용을 기반으로 한 결과나 데이터를 기반으로 한 인사이트가 도출 된 내용이 포함
파일 구조 규칙
- 파일 확장자:
.html - DOCTYPE 선언으로 시작:
<!DOCTYPE html> - 언어 설정:
<html lang="ko"> - 문자 인코딩:
<meta charset="UTF-8"> - 뷰포트 설정:
<meta name="viewport" content="width=device-width, initial-scale=1.0"> - 제목 형식:
<title>분석 보고서 대시보드</title>(또는 유사한 주제 기반 제목)
외부 리소스
- Tailwind CSS:
<script src="https://cdn.tailwindcss.com/3.4.16"></script> - Feather Icons:
<script src="https://unpkg.com/[email protected]"></script> - ApexCharts:
<script src="https://unpkg.com/[email protected]"></script> - Pretendard 폰트:
<link rel="stylesheet" as="style" crossorigin href="https://cdn.jsdelivr.net/gh/orioncactus/[email protected]/dist/web/static/pretendard.min.css" />
CSS 스타일 규칙
- 루트 변수 정의:
- 사용자가 색상을 제공하지 않을 경우 기본값 사용:
:root { --primary-color: #8A6AF2; /* 기본값, 사용자 지정 시 대체 */ --primary-light: #B39DFF; /* 기본값, 사용자 지정 시 대체 */ --primary-dark: #6845E0; /* 기본값, 사용자 지정 시 대체 */ --accent-color: #F3F0FF; /* 기본값, 사용자 지정 시 대체 */ --text-primary: #333; --text-secondary: #666; } - 사용자 요청 시: 사용자가 제공한 색상으로
--primary-color,--primary-light,--primary-dark,--accent-color를 동적으로 설정
- 사용자가 색상을 제공하지 않을 경우 기본값 사용:
- 기본 스타일:
- 폰트:
font-family: 'Pretendard', sans-serif; - 배경색:
background-color: #F8F7FC;(사용자가 요청 시 변경 가능) - 텍스트 색상:
color: var(--text-primary);
- 폰트:
- 클래스 기반 스타일:
.dashboard-card: 흰색 배경, 둥근 모서리 (rounded-lg), 그림자 효과 (shadow-md), 호버 시 살짝 올라가는 애니메이션 (hover:-translate-y-1).card-header: 하단 경계선 (border-b), 플렉스 레이아웃 (flex justify-between items-center), 제목 스타일.analysis-section: 왼쪽 테두리 (border-l-4) 색상은var(--primary-color), 배경색var(--accent-color).header-section: 그라데이션 배경 (bg-gradient-to-r from-[var(--primary-light)] to-[var(--primary-color)]), 둥근 모서리, 그림자 효과.stat-card: 중앙 정렬 (text-center), 그림자 포함 (shadow-sm)
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.
- 3d ago First seen · 115 lines · 8 tokens per session scan A 4ed13e68e543
report is a cursor rule published in the GitHub repository Mineru98/mysql-mcp-server (28 stars, last pushed 1y ago), licensed MIT. It adds 8 tokens to every session and 1,623 once invoked, about $0.0000 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 2026-08-30.
Other cursor rules, from other repositories
internationalization
Cursor rule "internationalization" from dtyq/magic, covering internationalization (i18n) rules, 国际化基本规范, 1. 文件结构, 2. 命名空间规范 and 3. 组件中使用国际化.
i18n
USE WHEN: Managing translation files (JSON), localization keys, or implementing multi-language logic.
i18n-translation-system
This project implements an intelligent translation system with incremental detection and language validation.
mf-expo-ship-checklist
When mf-expo work is finished — i18n, API usage, CHANGELOG.
controlflow-docs-evals
Rules for documentation parity, localized tutorials, and eval verification.
frontend-translation-management
Maintain consistent translation practices across the frontend application to ensure proper internationalization and user experience.