The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to perform environment discovery using the ls command to scan specific directories (~/.claude/skills/, etc.) for installed companion skills. This is a discovery mechanism used to identify which tools are present to provide context-aware recommendations.
[PROMPT_INJECTION]: The skill is designed to process and refactor user-provided source code, which introduces an indirect prompt injection surface.
Ingestion points: The agent ingests external source code provided by the user for architectural analysis (SKILL.md).
Boundary markers: There are no explicit delimiters to isolate external content from the agent's core instructions.
Capability inventory: The agent has shell execution access, evidenced by the environment check command (SKILL.md).
Sanitization: No explicit validation or sanitization mechanisms are defined for the ingested code.
[EXTERNAL_DOWNLOADS]: The skill documentation recommends installing further architectural components from a third-party registry (AbsolutelySkilled) using npx.

clean-architecture