The Agent Skills Directory

[SAFE]: The skill's primary function is local context management. It restricts its operations to reading and writing Markdown files within the mnemonic/ directory to preserve design history.
[PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by requiring the agent to read and follow context from stored notes. Ingestion points: Markdown files in the mnemonic/ directory. Boundary markers: Absent; notes are read into the agent's context without explicit delimiters or instructions to ignore embedded commands. Capability inventory: Local file system read and write access only; no network or shell execution capabilities are present. Sanitization: No validation or sanitization of note content is defined. This surface is considered safe given the skill's purpose and limited capabilities.

mnemonic-memory