The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the command git log --oneline -20 to retrieve recent commit history for project context. This is a read-only operation and uses a hardcoded limit.
[PROMPT_INJECTION]: The skill processes user task descriptions and Git history as untrusted input. Ingestion points: The feature-or-task-description argument and output from git log. Boundary markers: None explicitly defined; the skill relies on the agent's internal reasoning. Capability inventory: Read-only access via git log and file-write access to the docs/plans/ directory. Sanitization: None. This surface is considered low risk given the skill's restricted capabilities and primary purpose.
[SAFE]: No critical vulnerabilities, such as credential theft or remote code execution, were detected. The skill promotes security best practices by requiring design review and documentation before code changes.

brainstorming