majiayu000 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
Use when:
- Have implementation plan
- Tasks mostly independent
- Want to stay in this session
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
- Read plan, extract all tasks with full text, note context, create TodoWrite
- For each task:
- Dispatch implementer subagent (./implementer-prompt.md)
- Answer questions if subagent asks
- Subagent implements, tests, commits, self-reviews
- Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)
- If spec issues: implementer fixes, re-review
- Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)
- If quality issues: implementer fixes, re-review
- Mark task complete
- After all tasks: dispatch final code reviewer for entire implementation
- Use gremlins:finishing-a-development-branch
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 files from plans/active/{plan}/implementation/]
[Extract all 5 tasks with full text and context]
[Create TodoWrite with all tasks]
Task 1: Hook installation script
[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/gremlins/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
[Dispatch code quality reviewer]
Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.
[Mark Task 1 complete]
Task 2: Recovery modes
...
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
- 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 done
- 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
Integration
Required workflow skills:
- gremlins:writing-plans - Creates the plan this skill executes
- gremlins:requesting-code-review - Code review template for reviewer subagents
- gremlins:finishing-a-development-branch - Complete development after all tasks
Subagents should use:
- gremlins:test-driven-development - Subagents follow TDD for each task
Alternative workflow:
- gremlins:executing-plans - Use for parallel session instead of same-session execution