The Agent Skills Directory

[SAFE]: The skill consists of natural language instructions only and does not contain any executable scripts, binaries, or references to external code packages.
[COMMAND_EXECUTION]: The instructions direct the agent to utilize standard git utilities (git status, git diff --stat, and git log) to gather factual data about repository changes. These are typical, non-destructive development commands used within the scope of the agent's expected workspace.
[DATA_EXFILTRATION]: There are no network-capable commands or external URL references. Additionally, the skill includes a specific safety instruction prohibiting the inclusion of secrets, tokens, or full file contents in the generated handoff snippet, demonstrating a security-conscious design.

fyi