For many of us (including me), a coding agent that can read and edit files in your repository directly is out of reach. Since regular chatbots generally have generous free tiers, that is what I use regularly for coding.
Sometimes I want to give the chatbot some context about my existing code. What I generally do is copy and paste the relevant files, put them in code blocks, and type in the paths to those files.
However, giving the chatbot an idea of how the overall project is structured (files and folders) is crucial for optimal outputs. Doing this manually is really hard.
What I used to do was run the tree
command and copy its output. But this includes files that are not included in version control (such as node_modules
), which can get high in number and clutter the output. I found out that I can use the --gitignore
flag to only include tracked files, but the overall workflow was still slow.
I found some good options online (such as RepoMix), but they seemed to be much more complex than what I needed or optimized for slightly different things.
So, with the help of AI, I quickly created a Python app optimized for my specific workflow. Here is how it works.
The installation is super simple. You can run the command pip install reptclip
(or pipx
in Ubuntu) to install and use the app.
When you run the app from your terminal, relevant parts of your codebase, such as the project structure and the files you specify, are copied to your clipboard. You can paste it into the chat box and start typing your prompt right away.
For example, an output might look like this:
AGENTS.md README.md docs/README.md src/main.py src/functions.py
Contents of AGENTS.md
Contents of main.py
<- cursor will be here,
you can quickly start typing your prompt
You can use the -i
or --include
and -e
or --exclude
flags to specify which files to include. Glob patterns (**
and *
) as well as relative paths are supported. Simply running the command without any arguments (reptclip
or rrcc
) will only copy the project structure. Even that only saves a ton of time for a lot of people. Click here for basic usage instructions.
I also added an alias rrcc
so that you can launch the app either using the full name reptclip
or the quicker rrcc
command from the terminal. rrcc
can be typed using only your left hand.
Moreover, you can create a reptclip-config.toml
file (use the config
command to create a default one) in the root of your repository for default include and exclude patterns for a specific project. The config file also supports presets, which you can define in the config file and select one or more of them using -p
or --preset
flag (see Advanced Usage for more details). The content of files over 1MB and binary files is not pasted, and a placeholder mentioning the reason is included instead. Binary files are identified using their extensions as well as their content.
Thank you for reading till the end. If you found this app useful, please consider starring the repo and liking this post. I couldn't find an app that does this better, but if it does, I would love to know it. If you have any suggestions, please let me know. Pull requests are welcome, and I will be very happy to know what you think!
If you think that I am overstating such a simple project, I wouldn't blame you. I am just an 18-year-old kid (about to start college), anyway 🙂
Thanks for your support!