deep-plan

/deep-plan, a Claude Code plugin

Blog posts:

• Building /deep-plan - The story behind this plugin
• The Deep Trilogy - How the three plugins work together
• What I Learned - Technical lessons from plugin development

/deep-plan transforms vague feature requests into detailed, production-ready implementation plans through AI-assisted research, stakeholder interviews, and multi-LLM review.

/deep-implement, its companion plugin, takes these section files and implements them with TDD methodology, integrated code review, and atomic commits.

For large projects with broad, vague requirements, use /deep-project first to decompose into focused planning units before running /deep-plan on each.

This plugin started as an effort to automate the most time-intensive part of my Claude Code workflow that I had previously been doing manually. It is primarily targeted at Claude Code users that don't have strict token constraints and prefer deep planning/plan review before implementation. It's designed to speed up creating production-ready code within Claude Code without sacrificing an understanding of how it works.

TL;DR

/plugin marketplace add piercelamb/deep-plan
/plugin install deep-plan
/plugin enable deep-plan
/deep-plan @planning/auth-spec.md

Table of Contents

• Overview
• The Deep Trilogy
• Why deep-plan?
• When to Use
• Quick Start
• How It Works
• Installation
• Usage
• Workflow Steps
• Output Files
• Configuration
• Environment Variables
• Requirements
• Best Practices
• Security & Privacy
• Troubleshooting
• Testing
• Project Structure
• Contributing
• Changelog

Overview

deep-plan orchestrates a comprehensive planning workflow that ensures you think through implementation details before writing code:

Research → Interview → External LLM Review → TDD Plan → Section Splitting

The plugin guides you through:

• Research Phase: Analyze existing codebases and research the web for current best practices
• Interview Phase: Structured Q&A to surface hidden requirements and edge cases
• External Review: Independent feedback from Gemini, OpenAI, or an Opus subagent on your plan
• TDD Phase: Define test stubs before implementation
• Section Phase: Split into parallelizable, self-contained implementation units (written in parallel via subagents)

By the end, you have a complete planning directory with specs, research, reviews, and small, isolated implementation sections that any engineer (or Claude) can pick up cold.

The Deep Trilogy

This plugin is part of a three-plugin pipeline for turning ideas into production code:

/deep-project (decompose) → /deep-plan (plan) → /deep-implement (build)