The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands like git log, git status, find, and head to retrieve the current state of the project. These operations are restricted to the local environment and are used to provide the user with a summary of recent changes and active work items.
[PROMPT_INJECTION]: The skill processes untrusted data from the local repository that could serve as a surface for indirect prompt injection.
Ingestion points: Content is read from BACKLOG.md, .planning/*/whats-next.md, .planning/*/BRIEF.md, and the output of git log.
Boundary markers: No specific delimiters or safety instructions are used to separate ingested file content from the agent's core instructions.
Capability inventory: The agent is authorized to use Read, Shell, Glob, and Grep tools.
Sanitization: No content validation or sanitization is performed on the data retrieved from the file system or command outputs.

start