The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill identifies and updates domain concepts by reading existing repository documentation and source code, creating a surface for potential instructions embedded within that data.
Ingestion points: Processes CONTEXT.md, CONTEXT-MAP.md, Architecture Decision Records (ADRs) in docs/adr/, and repository source code in src/ to verify domain logic consistency.
Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potentially malicious content embedded within these files.
Capability inventory: The agent possesses the capability to read and write files within the repository and interact with the user to modify the domain model.
Sanitization: No explicit sanitization or validation of the content read from these repository files is instructed.

domain-modeling