tokendiet_skeletonize_code
Skeletonize Python files by keeping imports, signatures, docstrings, and focus symbols while eliding long unfocused helper bodies to reduce token usage before inference.
Instructions
AST-skeletonize Python files by keeping imports, signatures, docstrings, and focus symbols while eliding long unfocused helper bodies.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"source": "<source>"
},
"name": "tokendiet_skeletonize_code"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | ||
| focus_symbols | No | ||
| min_elide_lines | No |