The Agent Skills Directory

[SAFE]: The skill operates as a purely instructional workflow for the agent to locate and analyze specific project artifacts (plans, todos, handovers, and documentation) within the local filesystem.
[SAFE]: No network operations, external downloads, or remote code execution patterns were detected in the skill's logic or workflow.
[SAFE]: Access is limited to project-specific paths such as plans/ and docs/, with no attempts to read sensitive system files (e.g., SSH keys, credentials) or perform persistence-related tasks.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from local project files which could potentially contain malicious instructions intended for the agent. • Ingestion points: The agent reads plan artifacts from the plans/ directory and module documentation from the docs/ directory. • Boundary markers: No explicit delimiters or safety instructions are defined to separate document content from agent instructions. • Capability inventory: The skill has the capability to use the question tool to interact with the user and can delegate analysis to doc-explorer. • Sanitization: No content validation or sanitization mechanisms are described for the artifacts being processed.

resume-plan