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

mermaid

flowchart LR
  have_plan{"Have implementation plan?"}
  tasks_independent{"Tasks mostly independent?"}
  stay_session{"Stay in this session?"}
  subagent["subagent-driven-development"]
  executing["executing-plans"]
  manual["Manual execution or brainstorm first"]

  have_plan -->|yes| tasks_independent
  have_plan -->|no| manual
  tasks_independent -->|yes| stay_session
  tasks_independent -->|"no - tightly coupled"| manual
  stay_session -->|yes| subagent
  stay_session -->|"no - parallel session"| executing

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

mermaid

flowchart TB
  subgraph cluster_per_task["Per Task"]
    d_impl["Dispatch implementer subagent (./implementer-prompt.md)"]
    q_impl{"Implementer subagent asks questions?"}
    ans["Answer questions, provide context"]
    impl["Implementer subagent implements, tests, commits, self-reviews"]
    d_spec["Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)"]
    spec_ok{"Spec reviewer subagent confirms code matches spec?"}
    fix_spec["Implementer subagent fixes spec gaps"]
    d_quality["Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)"]
    quality_ok{"Code quality reviewer subagent approves?"}
    fix_quality["Implementer subagent fixes quality issues"]
    mark["Mark task complete in TodoWrite"]
  end

  read_plan["Read plan, extract all tasks with full text, note context, create TodoWrite"]
  more_tasks{"More tasks remain?"}
  final_review["Dispatch final code reviewer subagent for entire implementation"]
  finish["Use superpowers:finishing-a-development-branch"]

  read_plan --> d_impl
  d_impl --> q_impl
  q_impl -->|yes| ans
  ans --> d_impl
  q_impl -->|no| impl
  impl --> d_spec
  d_spec --> spec_ok
  spec_ok -->|no| fix_spec
  fix_spec --> d_spec
  spec_ok -->|yes| d_quality
  d_quality --> quality_ok
  quality_ok -->|no| fix_quality
  fix_quality --> d_quality
  quality_ok -->|yes| mark
  mark --> more_tasks
  more_tasks -->|yes| d_impl
  more_tasks -->|no| final_review
  final_review --> finish

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

code

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:using-git-worktrees - REQUIRED: Set up isolated workspace before starting
•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