The Agent Skills Directory

[SAFE]: The skill is a productivity utility designed for local context management. It does not perform any network operations, external downloads, or execution of arbitrary code.
[CREDENTIALS_UNSAFE]: The skill contains a dedicated 'Security Boundary' section that explicitly prohibits the persistence of secrets. It provides clear instructions and examples (redaction) to ensure that the AI agent does not inadvertently store API keys, tokens, or passwords in the memory.md file.
[PROMPT_INJECTION]: The skill reads instructions from local project files (such as CLAUDE.md or .cursorrules), which represents a potential surface for indirect prompt injection. However, this is mitigated by a mandatory confirmation step where the agent must summarize the restored state and wait for developer verification before continuing with the session.

remember