Lobster Subagent-Driven Development 🦞#

Fresh subagent per task. Two-stage review. Ship with confidence.

Inspired by Superpowers by Jesse Vincent.

Core Principle#

text

Fresh subagent per task + 2-stage review = high quality, fast iteration

Subagents never inherit session context. You construct exactly what they need. This preserves your own context for coordination work.

The Process#

1. Read Plan → Extract Tasks#

• Read implementation plan once
• Extract ALL tasks with full text
• Create TodoWrite tracking

2. Per Task: Implementer → Spec Review → Quality Review#

text

[Dispatch Implementer]
  ↓ (if questions → answer → re-dispatch)
[Implementer: implement + test + commit + self-review]
  ↓
[Dispatch Spec Reviewer]
  ↓ ❌ → Fix → Re-review
  ↓ ✅
[Dispatch Code Quality Reviewer]
  ↓ ❌ → Fix → Re-review
  ↓ ✅
[Mark task complete]
  ↓
[Next task...]

3. Final Review#

After all tasks complete:

• Dispatch final code reviewer for entire implementation
• Verify all requirements met
• Run full test suite

Model Selection#

Task TypeModelWhy1-2 files, complete specCheapestMechanicalMulti-file integrationStandardNeeds judgmentArchitecture/reviewStrongestNeeds expertise

Agent Status Handling#

StatusActionDONEProceed to spec reviewDONE_WITH_CONCERNSRead concerns, then decideNEEDS_CONTEXTProvide context, re-dispatchBLOCKEDChange model / split task / escalate

Never#

• Skip reviews (spec OR quality)
• Start quality review before spec passes
• Let implementer self-review replace actual review
• Move to next task while review has open issues
• Dispatch multiple implementers in parallel (conflicts)