The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local analysis script, scripts/find-god-files.py, to identify code duplication and file complexity. It also utilizes standard command-line tools such as rg (ripgrep), sed, sort, and uniq for reconnaissance and pattern matching within the target codebase.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process the contents of an external codebase.
Ingestion points: The skill reads source code files (.ts, .tsx, .js, .jsx) throughout the repository via rg and the find-god-files.py script (SKILL.md, scripts/find-god-files.py).
Boundary markers: There are no explicit instructions to the agent to disregard instructions or malicious prompts embedded within the source code comments or strings being analyzed.
Capability inventory: The skill has the capability to write to the filesystem, move files, create new packages, and execute local scripts (SKILL.md, references/package-extraction.md).
Sanitization: There is no specific evidence of sanitization, escaping, or filtering of the ingested source code content before it is processed by the agent.

componentize