The Agent Skills Directory

[COMMAND_EXECUTION]: The Python script scripts/concept_index.py performs repository analysis by executing Git commands such as git diff, git status, and git rev-parse. The script uses subprocess.run with argument lists rather than shell strings and explicitly avoids shell=True, which is a standard security practice to prevent command injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The file references/further-reading.md contains numerous links to well-known developer resources and blogs (e.g., martinfowler.com, sandimetz.com, and industry-standard documentation sites). These are provided as educational references for the agent and do not involve the automated download or execution of external code.
[DATA_EXPOSURE]: The skill analyzes repository structures, file paths, and conceptual patterns. It does not contain instructions or code intended to access sensitive information such as API keys, SSH credentials, or environment variables.

abstraction-architect