The Agent Skills Directory

[COMMAND_EXECUTION]: Includes a Python script (scripts/memory_audit.py) designed to diagnose the health of Claude Code memory files. The script performs read-only operations to check for line count violations, broken pointers, and missing metadata within the project's memory directory (typically located in ~/.claude/projects/).
[EXTERNAL_DOWNLOADS]: The README mentions installation via npx from the author's GitHub repository, which is a standard distribution method for this type of tool.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The skill's instructions and included script are consistent with its stated purpose of enhancing the performance and organization of an agent's persistent memory system.

agent-memory-implementation