claudegoodies
Skill

subagent-driven-development

From NousResearch

Execute plans via delegate_task subagents (2-stage review).

Dispatches a fresh subagent per plan task, running spec and code-quality reviews before marking each task complete.

Use it when

  • You have a written implementation plan with mostly independent tasks
  • You want automated spec-compliance and quality review between tasks
  • Executing multi-step features via delegate_task-capable subagents
  • Need consistent TDD-style workflow enforced per task

Skip it if

  • Tasks overlap on the same files, causing subagent conflicts
  • No plan file exists yet (must use a planning step first)
  • Requires a delegate_task/subagent orchestration system, not standalone code
  • Tasks are too small or too tightly coupled for 2-5 minute granularity

Facts

Repository
NousResearch/hermes-agent
Status
Actively maintained
Last commit
Source file
optional-skills/software-development/subagent-driven-development/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

# Subagent-Driven Development

## Overview

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

**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration.

## When to Use

Use this skill when:
- You have an implementation plan (from the `plan` skill or user requirements)
- Tasks are mostly independent
- Quality and spec compliance are important
- You want automated review between tasks

**vs. manual execution:**
- Fresh context per task (no confusion from accumulated state)
- Automated review process catches issues early
- Consistent quality checks across all tasks
- Subagents can ask questions before starting work

## The Process

### 1. Read and Parse Plan

Read the plan file. Extract ALL tasks with their full text and context upfront. Create a todo list:

```python
# Read the plan
read_file("docs/plans/feature-plan.md")

# Create todo list with all tasks
todo([
    {"id": "task-1", "content": "Create User model with email field", "status": "pending"},
    {"id": "task-2", "content": "Add password hashing utility", "status": "pending"},
    {"id": "task-3", "content": "Create login endpoint", "status": "pending"},
])
```

**Key:** Read the plan ONCE. Extract everything. Don't make subagents read the plan file — provide the full task text directly in context.

### 2. Per
View full source on GitHub →

Other skills