Use when executing implementation plans with independent tasks in the current session

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. Core principle: Fresh subagent per task and two stage review can improve isolation and feedback; verify actual quality, latency and cost. When to Use vs. Executing Plans (parallel session): Same session (no context switch) Fresh subagent per task (no context pollution) Two stage review after each task: spec compliance first, then code quality Faster iteration (no human in loop between tasks) Host and authority prerequisites Use only delegation tools actually available and allowed for this task. Task, TodoWrite and superpowers names below are host specific examples, not bundled capabilities. The three local prompt templates are bundled; other superpowers skills/templates are external dependencies. When unavailable, use the equivalent task tracker and independent code/spec review directly rather than claim a subagent ran. Set global concurrency/cost/time limits and cancellation; subagents cannot expand authorization. Commits require the established repository workflow and assigned branch, and reviewer approval does not authorize pushing, merging or publishing. Inspect actual files and command evidence at the exact reviewed head before completion. The Process Prompt Templates ./implementer prompt.md Dispatch implementer subagent ./spec reviewer prompt.md Dispatch spec compliance reviewer subagent ./code quality reviewer prompt.md Dispatch code quality reviewer subagent Example Workflow Advantages vs. Manual execution: Require the relevant tests explicitly; subagents do not follow TDD automatically Fresh context per task (no confusion) Separate context does not isolate files; assign disjoint ownership or isolated checkouts Subagent can ask questions (before AND during work) vs. Executing Plans: Same session (no handoff) Continuous progress (no waiting) Review checkpoints automatic Efficiency gains: No file reading overhead (controller provides full text) Controller curates exactly what context is needed Subagent gets complete information upfront Questions surfaced before work begins (not after) Quality gates: Self review catches issues before handoff Two stage review: spec compliance, then code quality Review loops ensure fixes actually work Spec compliance prevents over/under building Code quality ensures implementation is well built Cost: More subagent invocations (implementer + 2 reviewers per task) Controller does more prep work (extracting all tasks upfront) Review loops add iterations But catches issues early (cheaper than debugging later) Red Flags Never: Skip reviews (spec compliance OR code quality) Proceed with unfixed issues Dispatch multiple implementation subagents in parallel (conflicts) Make subagent read plan file (provide full text instead) Skip scene setting context (subagent needs to understand where task fits) Ignore subagent questions (answer before letting them proceed) Accept "close enough" on spec compliance (spec reviewer found issues = not done) Skip review loops (reviewer found issues = implementer fixes = review again) Let implementer self review replace actual review (both are needed) Start code quality review before spec compliance is ✅ (wrong order) Move to next task while either review has open issues If subagent asks questions: Answer clearly and completely Provide additional context if needed Don't rush them into implementation If reviewer finds issues: Implementer (same subagent) fixes them Reviewer reviews again Repeat until approved Don't skip the re review If subagent fails task: Dispatch fix subagent with specific instructions The controller may repair directly when clearer or when subagents are unavailable; preserve the review and validation requirements. Integration Required workflow skills: superpowers:writing plans Creates the plan this skill executes superpowers:requesting code review Code review template for reviewer subagents superpowers:finishing a development branch Complete development after all tasks Subagents should use: superpowers:test driven development Subagents follow TDD for each task Alternative workflow: superpowers:executing plans Use for parallel session instead of same session execution Limitations Use this skill only when the task clearly matches the scope described above. Do not treat the output as a substitute for environment specific validation, testing, or expert review. Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

subagent-driven-development