Use when superpowers executing-plans is the correct fallback for an approved plan, especially when subagent dispatch is unavailable, tasks are tightly coupled, or the user explicitly wants single-thread execution.
This companion augments executing-plans. Core principle: execution mode must
be chosen before autonomy begins. executing-plans is the only fallback path
after subagent-first routing fails or is ruled out.
executing-plans is already relevant or subagent-first routing has been ruled outverify -> commit -> push -> PR -> clean updocs/superpowers/plans/ rootDo not use this when the current session can safely split work through
subagent-driven-development and dispatch can actually happen.
superpowers:subagent-driven-development first; then let its
enhance handle autonomy.executing-plans becomes the correct fallback and should take over
immediately.executing-plans.executing-plans is confirmed as the correct path, continue
automatically through implementation and normal finish steps.verify -> commit -> push -> PR -> clean up.| State | Behavior |
|---|---|
| Subagents available and plan splits cleanly | Route to subagent path first |
| Subagent dispatch cannot actually happen | Fall back here immediately |
| Subagents unavailable or task tightly coupled | Stay on executing-plans |
| Legacy flat plan path appears | Resolve to module plan path first |
| Push/PR succeeds | Keep going to cleanup |
| Remote/auth failure | Escalate |
executing-plans after subagent-first fails