The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using git and codegraph. These commands are used to identify the repository root, manage worktrees, and initialize graph tools.
[PROMPT_INJECTION]: No malicious prompt injection patterns were detected. The skill includes a specific step to sanitize input (replacing slashes, spaces, and unusual characters with dashes), which helps prevent command injection when user-provided branch or task names are interpolated into shell commands.

creating-worktrees