The Agent Skills Directory

[SAFE]: No security issues detected. The skill's behavior is strictly limited to architectural analysis and context mapping within the local project environment.
[COMMAND_EXECUTION]: The skill instructs the agent to check the git log to understand the temporal stability and evolution of the codebase.
[DATA_EXPOSURE]: The skill reads project-specific documentation such as docs/CONTEXT_MAP.md, docs/UBIQUITOUS_LANGUAGE.md, and CLAUDE.md to establish domain context. This is the primary intended purpose of the skill.
[PROMPT_INJECTION]:
Ingestion points: Documentation files (docs/*, CLAUDE.md) and the general codebase (file content and directory structure).
Boundary markers: Absent; the instructions do not specify delimiters when processing file content.
Capability inventory: No network access, file-write operations, or dangerous system commands are requested or implemented.
Sanitization: None; the agent is expected to process the file content as text to extract architectural concepts.

holistic