The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions and logic involve executing standard development commands such as git and gh (GitHub CLI). These are used to gather repository state (auth, branch info) and automate the creation of branches and pull requests as part of the planning process.
[EXTERNAL_DOWNLOADS]: The documentation provides manual instructions for the user to update the skill via git fetch and git checkout from a community repository. There is no automated or unauthenticated remote code execution logic within the skill itself.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests untrusted data to generate future agent instructions.
Ingestion points: Reads project file structures, existing Markdown plans, and memory indices from the local workspace.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the data ingested during the Research phase.
Capability inventory: The skill possesses the capability to execute shell commands (git, gh) and write Markdown files to the plans/ directory.
Sanitization: No explicit sanitization or validation of the ingested repository content is mentioned before it is used to generate construction plans.

blueprint