The Agent Skills Directory

[SAFE]: The skill operates by reading local project files, such as conventions, specifications, and architecture decision records, to build a context-aware configuration for the OpenSpec framework. This behavior is restricted to the local file system and aligns with the stated purpose.- [SAFE]: No network operations, data exfiltration patterns, or attempts to access sensitive system credentials were found. The skill relies on bundled templates and existing project documentation.- [PROMPT_INJECTION]: The skill contains instructional rules for the agent to follow when generating artifacts (e.g., following TDD, adhering to architecture principles). These are standard operational guidelines for the HSDD methodology and do not constitute an attempt to bypass safety filters or override core agent instructions.- [SAFE]: The skill includes integrity checks, such as verifying Git submodule pointers and phase dependencies, which serve as functional safeguards to ensure the agent is working with the correct project state.

hsdd-config