The Agent Skills Directory

[SAFE]: The skill instructions and associated Python script focus on local repository analysis to identify file dependencies and edit targets. The included script scripts/build-context-map.py performs read-only operations on the local file system and uses standard library modules for search and text processing. It contains no network operations, credential harvesting, or persistence mechanisms. The risk assessment heuristics in the script (searching for tokens like 'auth' or 'secret' in filenames) are intended to warn developers about high-risk files during the planning phase.

context-map