Multi-Repo Workflow

Executes a requirement that spans multiple git repositories: plan once, then run one repository-scoped execution unit per repository (each running ss-coding-workflow from that repo's real working root), batched by dependency order, and finally consolidate all pull requests into one cross-repo report.

Why repository runners. Every unit must start with the target repository as its real working root so it loads that repo's own project instructions, specs, skills, and git state. Use a native child runner only when the host can guarantee an independent absolute working directory, fresh repository context, nested implementation/review delegation, observable lifecycle, and exact run identity. Otherwise use a fresh headless process. Extra file access without repository-scoped context is not sufficient.