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 + two-stage review (spec then quality) = high quality, fast iteration
When to Use
dot1digraph when_to_use { 2 "Have implementation plan?" [shape=diamond]; 3 "Tasks mostly independent?" [shape=diamond]; 4 "Stay in this session?" [shape=diamond]; 5 "subagent-driven-development" [shape=box]; 6 "executing-plans" [shape=box]; 7 "Manual execution or brainstorm first" [shape=box]; 8 9 "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"]; 10 "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"]; 11 "Tasks mostly independent?" -> "Stay in this session?" [label="yes"]; 12 "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"]; 13 "Stay in this session?" -> "subagent-driven-development" [label="yes"]; 14 "Stay in this session?" -> "executing-plans" [label="no - parallel session"]; 15}
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)
The Process
dot1digraph process { 2 rankdir=TB; 3 4 subgraph cluster_per_task { 5 label="Per Task"; 6 "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box]; 7 "Implementer subagent asks questions?" [shape=diamond]; 8 "Answer questions, provide context" [shape=box]; 9 "Implementer subagent implements, tests, commits, self-reviews" [shape=box]; 10 "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [shape=box]; 11 "Spec reviewer subagent confirms code matches spec?" [shape=diamond]; 12 "Implementer subagent fixes spec gaps" [shape=box]; 13 "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [shape=box]; 14 "Code quality reviewer subagent approves?" [shape=diamond]; 15 "Implementer subagent fixes quality issues" [shape=box]; 16 "Mark task complete in TodoWrite" [shape=box]; 17 } 18 19 "Read plan, extract all tasks with full text, note context, create TodoWrite" [shape=box]; 20 "More tasks remain?" [shape=diamond]; 21 "Dispatch final code reviewer subagent for entire implementation" [shape=box]; 22 "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen]; 23 24 "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "Dispatch implementer subagent (./implementer-prompt.md)"; 25 "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?"; 26 "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"]; 27 "Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)"; 28 "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"]; 29 "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)"; 30 "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" -> "Spec reviewer subagent confirms code matches spec?"; 31 "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"]; 32 "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [label="re-review"]; 33 "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="yes"]; 34 "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" -> "Code quality reviewer subagent approves?"; 35 "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"]; 36 "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="re-review"]; 37 "Code quality reviewer subagent approves?" -> "Mark task complete in TodoWrite" [label="yes"]; 38 "Mark task complete in TodoWrite" -> "More tasks remain?"; 39 "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"]; 40 "More tasks remain?" -> "Dispatch final code reviewer subagent for entire implementation" [label="no"]; 41 "Dispatch final code reviewer subagent for entire implementation" -> "Use superpowers:finishing-a-development-branch"; 42}
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
You: I'm using Subagent-Driven Development to execute this plan.
[Read plan file once: docs/plans/feature-plan.md]
[Extract all 5 tasks with full text and context]
[Create TodoWrite with all tasks]
Task 1: Hook installation script
[Get Task 1 text and context (already extracted)]
[Dispatch implementation subagent with full task text + context]
Implementer: "Before I begin - should the hook be installed at user or system level?"
You: "User level (~/.config/superpowers/hooks/)"
Implementer: "Got it. Implementing now..."
[Later] Implementer:
- Implemented install-hook command
- Added tests, 5/5 passing
- Self-review: Found I missed --force flag, added it
- Committed
[Dispatch spec compliance reviewer]
Spec reviewer: ✅ Spec compliant - all requirements met, nothing extra
[Get git SHAs, dispatch code quality reviewer]
Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.
[Mark Task 1 complete]
Task 2: Recovery modes
[Get Task 2 text and context (already extracted)]
[Dispatch implementation subagent with full task text + context]
Implementer: [No questions, proceeds]
Implementer:
- Added verify/repair modes
- 8/8 tests passing
- Self-review: All good
- Committed
[Dispatch spec compliance reviewer]
Spec reviewer: ❌ Issues:
- Missing: Progress reporting (spec says "report every 100 items")
- Extra: Added --json flag (not requested)
[Implementer fixes issues]
Implementer: Removed --json flag, added progress reporting
[Spec reviewer reviews again]
Spec reviewer: ✅ Spec compliant now
[Dispatch code quality reviewer]
Code reviewer: Strengths: Solid. Issues (Important): Magic number (100)
[Implementer fixes]
Implementer: Extracted PROGRESS_INTERVAL constant
[Code reviewer reviews again]
Code reviewer: ✅ Approved
[Mark Task 2 complete]
...
[After all tasks]
[Dispatch final code-reviewer]
Final reviewer: All requirements met, ready to merge
Done!
Advantages
vs. Manual execution:
- Subagents follow TDD naturally
- Fresh context per task (no confusion)
- Parallel-safe (subagents don't interfere)
- 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:
- Start implementation on main/master branch without explicit user consent
- 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
- Don't try to fix manually (context pollution)
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
