explaingit

gsd-build/get-shit-done

🔥 Hot62,925JavaScriptAudience · developerComplexity · 2/5ActiveLicenseSetup · easy

TLDR

A workflow system that keeps AI coding assistants sharp on long projects by breaking work into focused phases with fresh context windows, preventing the quality decay that happens in extended conversations.

Mindmap

mindmap
  root((repo))
    What it does
      Prevents context rot
      Splits work into phases
      Maintains project state
      Fresh AI subagents
    How it works
      Initialize project
      Discuss and plan
      Execute in parallel
      Verify and ship
    Use cases
      Solo dev projects
      Multi-phase builds
      Long AI sessions
      Complex workflows
    Tech stack
      JavaScript
      npm package
      AI assistants
    Audience
      Solo developers
      AI tool users

Things people build with this

USE CASE 1

Build multi-phase software projects as a solo dev without losing quality as AI conversations get longer.

USE CASE 2

Organize complex features into structured phases with clear requirements, roadmaps, and verification steps.

USE CASE 3

Keep your main AI session lean by offloading heavy work to fresh subagent sessions with clean context.

USE CASE 4

Maintain a living project snapshot so you can pause, switch tools, and resume without re-explaining everything.

Tech stack

JavaScriptnpmNode.js

Getting it running

Difficulty · easy Time to first run · 5min
Use freely for any purpose including commercial, as long as you keep the copyright notice.

In plain English

Get Shit Done (GSD) is a workflow system designed to help solo developers build software more reliably with AI coding assistants like Claude Code, Cursor, Windsurf, or Codex. The core problem it solves is "context rot", the well-known issue where the longer a conversation with an AI assistant runs, the worse the quality of its output becomes because the AI's working memory fills up with irrelevant history. GSD addresses this with a structured six-step loop: initialize a project (collecting requirements and generating a roadmap), discuss each phase (capturing design decisions before planning), plan each phase (research, create tasks, verify the plan), execute the phase (run tasks in parallel using fresh AI subagents, each with a clean context), verify the work (walk through what was built and diagnose failures), and then ship (create a pull request). By routing the heavy lifting into dedicated subagent sessions that each start with a clean context window, your main session stays lean and the quality stays consistent. Between sessions, GSD maintains a set of structured planning files, a project vision document, requirements, roadmap, and a current-state snapshot, so that when you start a new session the AI can immediately pick up where it left off without needing you to re-explain the entire project. You would use GSD if you are a solo developer who relies heavily on AI coding tools and finds that complex, multi-phase projects tend to go off the rails as sessions get longer or as context accumulates. It is installed via npm and works as a layer on top of whichever AI coding runtime you prefer. The tech stack is JavaScript (distributed as an npm package), and it works across macOS, Windows, and Linux. No particular backend framework is required, it installs into your existing AI coding workflow.

Copy-paste prompts

Prompt 1
Set up a GSD workflow for my project: initialize with requirements, create a roadmap, then execute the first phase using fresh subagents.
Prompt 2
I'm using Claude Code and my conversations are getting messy. How do I use GSD to split my project into phases and keep context clean?
Prompt 3
Show me how to use GSD's planning files (vision, requirements, roadmap) to hand off work between AI coding sessions without losing context.
Prompt 4
Walk me through the GSD six-step loop: initialize, discuss, plan, execute, verify, and ship for a feature I'm building.
Prompt 5
How do I run GSD tasks in parallel with separate AI subagents so each one starts with a fresh context window?
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.