The Agent Skills Directory

[SAFE]: The skill follows security best practices by requiring explicit user confirmation before performing file system operations, such as creating the docs/adr/ directory or writing new ADR files.
[SAFE]: No suspicious network activity, external dependencies, or obfuscated code were detected. The skill's functionality is limited to managing documentation within a standard project sub-directory and does not attempt to access sensitive files or escalate privileges.
[SAFE]: The tool incorporates a human-in-the-loop workflow, presenting drafts to the user for review and approval before any persistent changes are made to the codebase.

architecture-decision-records