The Agent Skills Directory

[COMMAND_EXECUTION]: The utility scripts index.py and _ontology.py execute local shell commands using the subprocess module.
Evidence: The scripts specifically invoke git rev-parse to retrieve the repository's short SHA and branch name.
Purpose: This repository metadata is used to populate a 'Git Context' section in the generated INDEX.md files, facilitating drift detection between documentation and code.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process documentation files from the local filesystem, which creates a potential surface for processing untrusted content.
Ingestion points: Markdown files located in the docs/ directory are parsed during health audits and inquiry modes.
Boundary markers: The system utilizes INDEX.md files as structural anchors to manage and limit the loading of document context.
Capability inventory: The agent is empowered to read and write documentation files and execute the included Python scripts for project management.
Sanitization: The _ontology.py utility employs yaml.safe_load() for parsing frontmatter, which prevents the execution of arbitrary Python objects during document processing.

code-docs