The Agent Skills Directory

[SAFE]: The skill logic is focused on a standard software development lifecycle and adheres to safety-conscious constraints, specifically excluding production release capabilities.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from external files such as handoff-from-pm.md and repo-runtime.md to drive repository modifications. However, it implements boundary markers by requiring a specific 'handoff package' to activate, and its capabilities are restricted to non-production code modifications (simulation in ~/oneos-prod), with explicit prohibitions on sensitive operations like MySQL writes or production releases.

oneos-dev-delivery