subagent-driven-development

Dispatch a fresh implementer subagent per task with a task brief file, then run a task reviewer subagent on the generated diff for spec compliance and code quality. After all tasks pass, dispatch a final whole-branch review before merging.

Subagent-driven development runs in the same session with a fresh subagent per task and automatic review checkpoints, enabling faster iteration. Executing plans uses a parallel session with human-in-the-loop handoffs between tasks.

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

Assess the blocker before retrying: provide more context for context problems, re-dispatch with 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 ledger file at .superpowers/sdd/progress.md records each completed task with its commit range. After compaction, check the ledger and git log to resume at the first incomplete task instead of re-dispatching finished work.

Avoid it when tasks are tightly coupled and cannot be implemented independently, when no written implementation plan exists yet, or when you prefer a parallel session with human review between tasks. Brainstorm or write the plan first in those cases.