promptpack-for-code
A command-line tool that bundles your code files into a single text or XML file, optimized for AI code review and analysis. It helps developers prepare their codebase for productive conversations with AI language models by combining multiple source files into a well-formatted context.
Installation
pip install promptpack-for-code
Usage
You can use the tool with its full name promptpack-for-code or with the convenient short aliases: ppc or packcode.
Basic usage with a single directory:
ppc /path/to/your/code
Process multiple directories:
ppc dir1 dir2 dir3
Specify root directory for tree structure and full relative paths:
ppc /path/to/specific/folder -r /path/to/project/root
Specify output file path (default is output.xml):
ppc /path/to/src -o /path/to/output/result.xml
Generate text output instead of XML (XML is now the default):
ppc /path/to/src --format text
Use full XML tags instead of compact format:
ppc /path/to/src --no-compact-xml
Ignore specific patterns:
ppc /path/to/src --ignore "*.log" "*.tmp"
Show progress bar during processing:
ppc /path/to/src --progress
Force overwrite existing output file:
ppc /path/to/src -f
Features
- Combines multiple source files from one or more directories into a single output file
- Generates a tree-like directory structure based on the specified root
- Preserves file structure with full relative paths from the root directory
- Supports both XML (default) and plain text output formats
- XML format has both compact and full-tag modes for different use cases
- Built-in ignore patterns for common files (e.g.,
.git,__pycache__, etc.) - Customizable output file path
- Optional progress bar for large projects
- Easy to integrate with various AI chat platforms
- Multiple command aliases:
promptpack-for-code,ppc, andpackcode
Output Formats
Text Format
The generated text output file contains:
- A tree-like representation of your project structure (based on the root directory)
- The contents of all files in the specified directories, with paths relative to the root
Example text output:
Project Directory Structure:
==========================
project-name
├── src
│ ├── main.py
│ └── utils
│ └── helper.py
└── tests
└── test_main.py
File Contents from Selected Directories:
===================================
====
File: src/main.py
----
[file content here]
XML Format
The generated XML output file provides a structured representation with:
- A hierarchical view of your project directory structure
- The contents of all specified files, with paths relative to the root
Compact XML (Default)
By default, the tool produces compact XML with minimal tags and no indentation to reduce file size. It includes a legend comment at the beginning of the file explaining all tags:
<!--
XML Tag Legend:
- p: project (root element)
- n: name (project name)
- s: structure (directory structure)
- d: directory
- f: file
- c: contents (file contents section)
- p attribute: path of file or directory
- s inside directory: skipped directory
- e: error
-->
<p><n>project-name</n><s><d p="src"><f p="main.py"/><d p="utils"><f p="helper.py"/></d></d><d p="tests"><f p="test_main.py"/></d></s><c><f p="src/main.py">[file content here]</f></c></p>
Full XML (with --no-compact-xml option)
For better readability, you can use the --no-compact-xml option to get full tags with proper indentation:
<project>
<name>project-name</name>
<structure>
<directory path="src">
<file path="main.py" />
<directory path="utils">
<file path="helper.py" />
</directory>
</directory>
<directory path="tests">
<file path="test_main.py" />
</directory>
</structure>
<contents>
<file path="src/main.py">
<content>
[file content here]
</content>
</file>
<!-- Other file contents -->
</contents>
</project>
The XML format offers better structure and is easier to parse programmatically, making it ideal for automated analysis or integration with other tools.
Command Aliases
For convenience, this tool provides three command aliases:
promptpack-for-code: The full nameppc: Short alias for quicker typingpackcode: Alternative alias
All commands provide identical functionality:
# These all do the same thing (generate compact XML by default):
promptpack-for-code /path/to/src
ppc /path/to/src
packcode /path/to/src
# These all generate text output:
promptpack-for-code /path/to/src --format text
ppc /path/to/src --format text
packcode /path/to/src --format text
Development
To contribute to this project:
- Clone the repository:
git clone https://github.com/changyy/py-promptpack-for-code.git
cd py-promptpack-for-code
- Install in development mode:
pip install -e .
Requirements
- Python 3.6+
- tqdm (for progress bar support)
License
MIT License - see LICENSE file for details
Metadata
Release files for promptpack-for-code 2.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| promptpack_for_code-2.1.1.tar.gz | 12.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| promptpack_for_code-2.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 23.2 kB
Release files / promptpack_for_code-2.1.1.tar.gz
| Download URL | promptpack_for_code-2.1.1.tar.gz |
|---|---|
| Size | 12.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
59e69d290cd1efc2d0575a4089d146b5c994f7ea9cd0260fa50a5d006bd9e02b
|
|
BLAKE2b-256 checksum How to use checksums |
52261e1cdadc5f331bd7bca3712679fc82302348b1e5f89a187df6f160933aa0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 4, 2025.
Transparency logRelease files / promptpack_for_code-2.1.1-py3-none-any.whl
| Download URL | promptpack_for_code-2.1.1-py3-none-any.whl |
|---|---|
| Size | 10.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
923babed22cbf0201abdd6308a3a10b395265acba1f49f53bda60e3eba5649de
|
|
BLAKE2b-256 checksum How to use checksums |
18c018e924ac4d0a6769ef79ad85fdec89cabc38ee42ffd95ec0334b5beb36a1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 4, 2025.
Transparency log