dump_codebase_context
Extract and organize text files from a directory, respect .gitignore, skip binaries, and segment output into chunks for efficient processing with LLMs.
Instructions
Recursively reads text files from a specified directory, respecting .gitignore rules and skipping binary files. Concatenates content with file path headers/footers. Supports chunking the output for large codebases.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| base_path | Yes | The absolute path to the project directory to scan. | |
| chunk_index | No | Optional 1-based index of the chunk to return (default: 1). Requires num_chunks > 1. | |
| num_chunks | No | Optional total number of chunks to divide the output into (default: 1). |
Input Schema (JSON Schema)
{
"properties": {
"base_path": {
"description": "The absolute path to the project directory to scan.",
"type": "string"
},
"chunk_index": {
"default": 1,
"description": "Optional 1-based index of the chunk to return (default: 1). Requires num_chunks > 1.",
"minimum": 1,
"type": "integer"
},
"num_chunks": {
"default": 1,
"description": "Optional total number of chunks to divide the output into (default: 1).",
"minimum": 1,
"type": "integer"
}
},
"required": [
"base_path"
],
"type": "object"
}