skills.rest
rinbarpen
rinbarpenCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Executes implementation plans by dispatching fresh subagents per task with two-stage review.

Updated Jan 12, 2025
Search Tags:#tdd#code review#workflow automation#implementation plan#subagent#spec compliance#task orchestration
One-click install
npx skills add https://github.com/rinbarpen/NeuroTrain --skill subagent-driven-development-rinbarpen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/rinbarpen/NeuroTrain/tree/main/.cursor/commands/subagent-driven-development
Command: npx skills add https://github.com/rinbarpen/NeuroTrain --skill subagent-driven-development-rinbarpen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Executing a multi-task implementation plan manually often leads to context pollution, skipped reviews, and inconsistent quality across tasks. This Skill orchestrates plan execution by dispatching a fresh subagent for each task and enforcing a two-stage review after every task. ## Core Features & Use Cases - Fresh Subagent Per Task: Each task runs in an isolated subagent context, preventing confusion and cross-task interference. - Two-Stage Review Gates: A spec compliance review verifies the code matches requirements exactly, followed by a code quality review before any task is marked complete. - Prompt Templates Included: Ready-to-use templates for the implementer, spec reviewer, and code quality reviewer subagents. - Use Case: Given a written plan with 5 independent tasks, the controller extracts all tasks, dispatches implementer subagents one at a time, runs both reviews per task, and finishes with a final whole-implementation code review. ## Quick Start Use subagent-driven development to execute the implementation plan in docs/plans/feature-plan.md task by task.

Frequently Asked Questions about subagent-driven-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute an implementation plan with subagents?▼

Read the plan once, extract all tasks with full text into a todo list, then dispatch one implementer subagent per task with the complete task text and context. After each task, run a spec compliance review followed by a code quality review before marking it complete.

What is the difference between subagent-driven development and executing plans?▼

Subagent-driven development runs in the same session with fresh subagents per task and continuous progress. Executing plans uses a parallel session with a handoff, which suits work you want isolated from the current conversation.

Why must spec compliance review come before code quality review?▼

Spec compliance confirms the right thing was built, while code quality confirms it was built well. Reviewing quality first wastes effort on code that may need rework to match the specification.

Can I dispatch multiple implementer subagents in parallel?▼

No. Parallel implementer subagents cause conflicts because they may edit the same files. Dispatch one implementer at a time and wait for both reviews to pass before starting the next task.

What happens when a reviewer finds issues in a task?▼

The same implementer subagent fixes the reported issues, then the reviewer re-reviews the changes. This loop repeats until the reviewer approves, and the task is only marked complete after both reviews pass.

Related Skills

Explore More Software Engineering Skills→
huangbaixunhuangbaixun
3

harness:subagent-driven-development

Dispatch isolated subagents to execute implementation plan tasks with spec and code quality reviews.

Community
Advanced
GuicedEEGuicedEE
5

finishing-a-development-branch

Verify tests, clean diffs, and prepare a development branch for review.

Official
Intermediate
ZxelaZxela

implement

Implement acceptance criteria through a test-driven development workflow.

Community
Advanced
lespacemanlespaceman
4

executing-plans

Execute written implementation plans in batches with human checkpoints.

Community
Advanced