subagent-driven-development

Read the plan once, create todos, then dispatch a fresh implementer subagent per task using the task brief extracted by the task-brief script. After each task, generate a review package and dispatch a task reviewer subagent before marking the task complete.

Subagent-driven development runs in the same session with a fresh subagent per task and automatic review checkpoints, while executing-plans runs in a parallel session with human handoffs. Choose subagent-driven development for faster iteration without context switching.

Always specify the model explicitly when dispatching. Use cheap models for mechanical single-file tasks with complete specs, standard models for multi-file integration work, and the most capable model for architecture decisions and the final whole-branch review.

Assess the blocker: provide more context and re-dispatch for context problems, use a more capable model for reasoning-heavy tasks, break oversized tasks into smaller pieces, or escalate to the human if the plan itself is wrong. Never force the same model to retry unchanged.

A progress ledger file at .superpowers/sdd/progress.md records each completed task with its commit range. After compaction, trust the ledger and git log over conversation memory, and never re-dispatch tasks the ledger marks complete.

Avoid it when there is no written implementation plan, when tasks are tightly coupled and cannot be delegated independently, or when a parallel session via executing-plans fits better. Brainstorm or write the plan first in those cases.