The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to manage the development environment through git worktrees. This includes commands such as git worktree add to create a workspace and git worktree remove to clean up after a pull request is created.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection because its core functionality involves surveying and reading untrusted repository content, including documentation and source code.
Ingestion points: The 'Scan' phase in Step 2 involves reading all project documentation and cross-referencing it against the codebase.
Boundary markers: No specific delimiters or boundary markers are defined to help the agent distinguish between its instructions and the data it reads from the repository.
Capability inventory: The agent has the capability to write to the local file system, commit changes to the repository, and open pull requests.
Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the content ingested from the project files during the scanning process.

garden