The Agent Skills Directory

[SAFE]: The skill primarily functions as a cognitive framework for planning, guiding the agent to generate documentation and structured tasks. It does not execute code, access sensitive files, or perform network requests.
[COMMAND_EXECUTION]: The instructions include templates for shell commands (e.g., git commit, pytest) intended to be part of the generated plan for future use. These commands are illustrative and are not executed by the skill itself during the planning process.
[DATA_EXPOSURE]: The skill directs the agent to save output documents to a specific project-relative path (docs/superpowers/plans/). This is a standard organizational practice for development artifacts and does not involve sensitive system directories or credential files.

writing-plans