The Agent Skills Directory

[SAFE]: The skill instructions focus exclusively on maintaining project documentation (CONTEXT.md and ADRs). It encourages best practices in domain-driven design by challenging vague terminology and cross-referencing user claims with project code.
[SAFE]: No external network requests, remote code execution patterns, or sensitive data exfiltration vectors were detected. The skill uses standard file system access to read and write markdown files within the project repository.
[INDIRECT_PROMPT_INJECTION]: The skill maintains an attack surface for indirect prompt injection as it reads project source code and documentation to validate domain terminology. While a malicious project could contain instructions hidden in code comments to influence the agent, the skill's capabilities are limited to markdown file modifications, and it does not possess high-risk tools like shell execution or network access in its defined scope.
Ingestion points: Reads CONTEXT.md, CONTEXT-MAP.md, and project source code files.
Boundary markers: None explicitly defined in the instructions for separating code content from instructions.
Capability inventory: Limited to reading project files and writing markdown documentation.
Sanitization: None specified; the agent relies on its inherent guardrails when processing project data.

domain-modeling