The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions intended to configure the agent's behavior for architectural reviews and plan interviews.
[SAFE]: No external dependencies, package installations (Python/Node.js), or remote script executions are present in the skill definition.
[SAFE]: There is no evidence of credential exposure, data exfiltration, or unauthorized file access. The instructions are transparent and aligned with the stated purpose.
[PROMPT_INJECTION]: The skill directs the agent to 'explore the codebase' to answer questions. This creates an attack surface for indirect prompt injection from codebase content. However, as the skill provides no administrative or dangerous capabilities (such as writing to the filesystem or making network calls), the risk is negligible.

grill-me