Multi-Repo Workflow

Executes a requirement that spans multiple git repositories: plan once, then run one headless sub-process per repository (each running ss-coding-workflow inside its own repo), batched by dependency order, and finally consolidate all pull requests into one cross-repo report.

Why processes, not subagents. A subagent inherits this session's configuration — it never loads the target repo's own project instructions, specs, or skills. A headless sub-process started with its working directory set to the target repo is a full, independent agent session that discovers that repo's own configuration natively, and can spawn its own implementer/reviewer subagents inside it. This gives two levels of parallelism without nesting subagents inside subagents.

Orchestrator (this session)
  ├── in repo-a: run ss-coding-workflow <plan-a>, autonomous, lite/full     ┐ batch 1 (parallel)
  ├── in repo-b: run ss-coding-workflow <plan-b>, autonomous, lite/full     ┘
  └── in repo-c: run ss-coding-workflow <plan-c>, autonomous, lite/full       batch 2 (after batch 1)