The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git commands to analyze repository history and utilizes dynamic context injection to retrieve tags and recent commits upon initialization.
[PROMPT_INJECTION]: The skill processes untrusted data from external sources, making it susceptible to indirect prompt injection.
Ingestion points: Data is gathered from git logs, sprint reports in production/sprints/, and design documents in design/gdd/.
Boundary markers: The skill does not utilize delimiters or specific instructions to isolate ingested data from agent instructions.
Capability inventory: The agent is granted access to the Bash, Read, Glob, and Grep tools.
Sanitization: No sanitization or validation is performed on the ingested content or user-provided arguments.

changelog