subagent-driven-development

SKILL.md

Dispatch fresh subagents per task with two-stage review (spec compliance, then code quality) in the current session.

Isolates each task to a dedicated subagent with precisely crafted context, preventing context pollution and keeping the controller focused on coordination

Enforces a two-stage review cycle: spec compliance reviewer confirms the implementation matches requirements, then code quality reviewer checks for issues

Handles implementer status signals (DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, BLOCKED) with appropriate escalation or re-dispatch logic

Recommends model selection by task complexity: cheap models for mechanical 1–2 file tasks, standard models for multi-file integration, most capable models for architecture and review

Requires git worktree setup upfront and integrates with test-driven development and finishing-a-development-branch superpowers

Subagent-Driven Development

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration

Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.

When to Use