メニュー
Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | Subagent-Driven Development |
| description | Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks |
| when_to_use | when executing implementation plans with independent tasks in the current session, using fresh subagents with review gates |
| version | 1.1.0 |
Execute plan by dispatching fresh subagent per task, with code review after each.
Core principle: Fresh subagent per task + review between tasks = high quality, fast iteration
vs. Executing Plans (parallel session):
When to use:
When NOT to use:
Read plan file, create TodoWrite with all tasks.
For each task:
Dispatch fresh subagent:
Task tool (general-purpose):
description: "Implement Task N: [task name]"
prompt: |
You are implementing Task N from [plan-file].
Read that task carefully. Your job is to:
1. Implement exactly what the task specifies
2. Write tests (following TDD if task says to)
3. Verify implementation works
4. Commit your work
5. Report back
Work from: [directory]
Report: What you implemented, what you tested, test results, files changed, any issues
Subagent reports back with summary of work.
Dispatch code-reviewer subagent:
Task tool (code-reviewer):
Use template at skills/collaboration/requesting-code-review/code-reviewer.md
WHAT_WAS_IMPLEMENTED: [from subagent's report]
PLAN_OR_REQUIREMENTS: Task N from [plan-file]
BASE_SHA: [commit before task]
HEAD_SHA: [current commit]
DESCRIPTION: [task summary]
Code reviewer returns: Strengths, Issues (Critical/Important/Minor), Assessment
If issues found:
Dispatch follow-up subagent if needed:
"Fix issues from code review: [list issues]"
After all tasks complete, dispatch final code-reviewer:
After final review passes, proceed to integrate the work (e.g. merge the branch locally, push and create a PR, or request feedback).
You: I'm using Subagent-Driven Development to execute this plan.
[Load plan, create TodoWrite]
Task 1: Hook installation script
[Dispatch implementation subagent]
Subagent: Implemented install-hook with tests, 5/5 passing
[Get git SHAs, dispatch code-reviewer]
Reviewer: Strengths: Good test coverage. Issues: None. Ready.
[Mark Task 1 complete]
Task 2: Recovery modes
[Dispatch implementation subagent]
Subagent: Added verify/repair, 8/8 tests passing
[Dispatch code-reviewer]
Reviewer: Strengths: Solid. Issues (Important): Missing progress reporting
[Dispatch fix subagent]
Fix subagent: Added progress every 100 conversations
[Verify fix, mark Task 2 complete]
...
[After all tasks]
[Dispatch final code-reviewer]
Final reviewer: All requirements met, ready to merge
Done!
vs. Manual execution:
vs. Executing Plans:
Cost:
Never:
If subagent fails task:
Pairs with:
Alternative to:
See code-reviewer template: skills/collaboration/requesting-code-review/code-reviewer.md
Designed to assist users with ADHD (Attention Deficit Hyperactivity Disorder) by mitigating task paralysis, managing distractions, providing dopamine-driven progress tracking, and using executive-friendly visual formatting. Triggered by keywords or topics: - Focus/Distraction: "adhd", "fokus", "distracted", "gampang bosan", "pecah fokus", "distraksi", "sulit konsentrasi". - Task Initiation/Paralysis: "bingung mulai", "task paralysis", "mager", "banyak tugas", "tumpuk", "stuck", "overwhelmed". - Motivation/Rewards: "dopamine", "reward", "game", "poin", "xp", "checkpoint". - Formats: "bionic reading", "visual salience", "micro-step", "body double".
Execute detailed plans in batches with review checkpoints
Prevent task duplication, file conflicts, and coordination failures when multiple subagents work in parallel on the same Superagent project. Covers both Superagent→Subagent coordination and Master Agent→Superagent worktree coordination. Uses manage_plan and manage_tasks as the coordination hub.
Create isolated git worktrees with smart directory selection and safety verification
Triggered when the agent needs to audit, discover, and resolve missing features, architectural or functional gaps, performance/process bottlenecks, and structural complexity liabilities across a codebase, delivering lean and pragmatic improvement blueprints.
Triggered when the agent needs to solve complex, multi-faceted problems by simulating the collective intelligence of 100 specialized minds divided into 6 functional teams (Strategy, Domain Experts, Red Team, Empirical Testers, Consensus Council, and Execution Ops) within a single agent session.