The Agent Skills Directory

[SAFE]: The skill operates strictly on the local file system within the target repository. It reads source code files and writes metadata and cache files to a dedicated .codemap/ subdirectory.
[SAFE]: No network operations, data exfiltration patterns, or external downloads were detected in the source code or scripts.
[SAFE]: The skill uses established and reputable dependencies, such as web-tree-sitter and tsx, for parsing and script execution.
[SAFE]: The skill's behavior is transparent and aligns with its stated purpose of providing a persistent structural index for codebase exploration.

codemap