The Agent Skills Directory

[SAFE]: The skill is intended for documentation generation and operates by scanning the local repository's directory structure and reading configuration files (e.g., package.json, go.mod) and source code. It does not perform any external downloads or execute remote scripts.\n- [SAFE]: There are no identified network operations or exfiltration paths. The skill's workflow is confined to reading architectural signals and writing the extracted documentation to the local 'codemaps/' directory.\n- [SAFE]: The skill identifies a data ingestion surface (Category 8) as it processes source code files to generate summaries. Ingestion points: source files and manifests. Boundary markers: none specified. Capability inventory: local file-system read and write. Sanitization: none specified. This surface is considered safe given the skill's primary purpose and its lack of high-risk capabilities such as network access or arbitrary command execution.

update-codemaps