The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a shell command using find to locate markdown files within the user's ~/.claude/projects/ directory structure. This is used for the intended purpose of scanning memory files.
[PROMPT_INJECTION]: The skill evaluates the contents of existing memory files which presents an indirect prompt injection surface. Instructions embedded in these files could potentially influence the agent's health assessment logic. * Ingestion point: Reading markdown files from ~/.claude/projects/*/memory as identified in SKILL.md. * Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions found within the processed files. * Capability inventory: The skill has permissions to read, move, and update files on the local file system. * Sanitization: No content validation or sanitization is performed on the data read from memory files before processing.

memory-cleanup