The Agent Skills Directory

[SAFE]: The skill is a utility for documentation hygiene, establishing a protocol for managing project-level metadata (AGENTS.md), backlogs, and changelogs. All activities are focused on file structure validation and internal documentation updates.
[COMMAND_EXECUTION]: The skill includes shell scripts (scripts/_bootstrap, scripts/validate-context, scripts/_self-test) that execute standard Unix utilities like grep, sed, awk, find, and stat. These commands are used appropriately for linting markdown files and verifying project structure, with no evidence of command injection or dangerous side effects.
[EXTERNAL_DOWNLOADS]: No external scripts or packages are downloaded or executed. The installation process (_bootstrap) is limited to copying internal scripts to the user's local bin directory.
[DATA_EXFILTRATION]: There are no network-related commands (e.g., curl, wget) or attempts to read sensitive files like credentials or SSH keys.

evolve-context