🔮 is-my-code-cursed

A CLI Tool That Roasts Your Code Using AI

An ancient code sage analyzes your code for cursedness — bad naming, spaghetti logic, magic numbers, and crimes against readability — then delivers a dramatic verdict with a curse rating from 1 to 10.

Features • Installation • Usage • Flags • Contributing

---

✨ Features

🔮 Dramatic AI Roasting An ancient code sage delivers a theatrical verdict on your code ⚔️ Brutal Mode No mercy mode for when you want the harshest possible roast 📄 Save Reports Export the sage's verdict to a file for future reference

📏 Word Limit Control how long the sage's rant is with a word limit flag 📁 Directory Support Analyze entire projects recursively, skipping binary files automatically 🛡️ Proper Error Handling Clear error messages for missing API keys, files, and API failures

---

🤔 Why This Project?

Ever stared at your own code and wondered if it's actually cursed? Now you can get a second opinion — from an ancient code sage powered by Gemini AI.

• 🧙 Dramatic verdicts — not just "this is bad", but a full theatrical roast with specific callouts
• 📊 Curse rating — get a score from 1 (barely cursed) to 10 (an abomination)
• ⚔️ Brutal mode — for when you really want to suffer
• 🛠 Learning project — built to learn CLI tool development and the Gemini API

---

🚀 Installation

Option 1: AUR (Arch Linux)

If you're on Arch Linux or an Arch-based distro, install directly via your AUR helper:

yay -S is-my-code-cursed

No dependencies to install manually — just set your API key and you're good to go.

Option 2: Manual

1. Clone the repository

git clone https://github.com/HimC29/is-my-code-cursed.git
cd is-my-code-cursed

2. Get a Gemini API key

Get a free API key from aistudio.google.com and add it to your shell config:

# Add to ~/.zshrc or ~/.bashrc
export GEMINI_API_KEY="your_key_here"

Then reload your shell:

source ~/.zshrc  # or ~/.bashrc

3. Install the CLI command

chmod +x install.sh
./install.sh

Now you can run is-my-code-cursed from anywhere!

---

📖 Usage

is-my-code-cursed <file|directory> [flags]

Basic example

is-my-code-cursed main.py

Analyze an entire project

is-my-code-cursed ./my-project

Save the verdict to a file

is-my-code-cursed main.py --output report.txt

Brutal mode (no mercy)

is-my-code-cursed main.py --brutal

Limit the response length

is-my-code-cursed main.py --max-words 300

Exclude directories

is-my-code-cursed ./my-project --exclude dist,build

Combine flags

is-my-code-cursed main.py --brutal --max-words 500 --output report.txt

---

🚩 Flags

Flag	Short	Description
--output FILE	-o	Save the sage's verdict to a file
--brutal	-b	No mercy mode — harsher roasting
--max-words N	-w	Limit the response to N words
--verbose	-v	Print status when calling the Gemini API
--exclude DIRS	-e	Comma-separated directories to ignore
--version		Print the version and exit
--help	-h	Show help message and exit

---

📁 Project Structure

is-my-code-cursed/
├── src/
│   └── main.py          — Main CLI script
├── install.sh            — Installs the CLI command system-wide
├── README.md             — Project documentation
└── LICENSE               — MIT license

---

📝 Changelog

v1.2.0

• 🏷️ Add --version flag to print the current version

v1.1.0

• 🔧 Removed python-google-generativeai dependency — now uses only Python stdlib
• 📡 Gemini API calls now made directly via urllib.request
• ⚠️ Improved warning message when a file is skipped during directory scan
• 📦 Much easier to install — no AUR dependencies required

From this version onwards, this project follows Semantic Versioning: MAJOR.MINOR.PATCH — breaking changes . new features . bug fixes

v1.0.5

• 💻 Add auto permission elevation for Linux installs in install.sh if needed

v1.0.4

• 🚫 New --exclude / -e flag to ignore custom directories
• 🧹 Support multiple excluded folders using comma-separated values

v1.0.3

• 📁 Add directory support — analyze entire projects recursively
• 🚫 Automatically skip binary files
• 🧹 Ignore common dependency/cache folders like .git and node_modules
• 📄 Include file names and contents in AI analysis context

v1.0.2

• 💻 Rename add_to_path.sh to install.sh
• Improve install.sh to support Termux and have more fallback features

v1.0.1

• 🧹 Small code cleanup
• New flag: --verbose to print status when importing lib and calling API

v1.0.0

• 🎉 Initial release
• AI-powered code roasting with curse rating 1-10
• --brutal mode for no mercy roasting
• --output to save reports to a file
• --max-words to control response length

---

📝 Example Output

Hark, seeker of truth! I have gazed upon thy digital parchment...

Curse Rating: 7/10

A heavy curse, indeed! Your code does not merely stumble; it actively
confesses its most heinous sin in plain sight...

---

🤝 Contributing

Contributions are welcome! If you have ideas for new flags, better prompts, or bug fixes, feel free to open an issue or PR.

How to Contribute

1. Fork the Project
2. Create your Feature Branch

   git checkout -b feature/AmazingFeature

3. Commit your Changes

   git commit -m 'Add some AmazingFeature'

4. Push to the Branch

   git push origin feature/AmazingFeature

5. Open a Pull Request

Ideas for Contributions

• 🎨 Colored terminal output with colorama or rich
• 🔔 Support for more languages/models
• 📦 PyPI package release

---

📄 License

Distributed under the MIT License. See LICENSE for more information.

---

⭐ Star this repo if your code got roasted!

Made with 🔮 by HimC29

Report Bug • Request Feature