GSD Core

---

What is GSD Core

GSD Core is a context-engineering and spec-driven development framework that drives AI coding agents (Claude Code, Codex, Gemini CLI, Copilot, Cursor, and more) through a disciplined phase loop. It solves context rot — the quality degradation that accumulates as an AI fills its context window — by running all heavy research, planning, and execution work in fresh-context subagents while keeping your main session lean.

---

How it works

Each milestone repeats the same five-step loop, one phase at a time:

1. Discuss — capture implementation decisions before anything is planned
2. Plan — research, decompose, and verify the plan fits a fresh context window
3. Execute — run plans in parallel waves; each executor starts with a clean 200k-token context
4. Verify — walk through what was built; diagnose and fix before declaring done
5. Ship — create the PR, archive the phase, repeat for the next one

---

Quickstart

npx @opengsd/gsd-core@latest

The installer prompts for your runtime (Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf, and more) and whether to install globally or locally. The installer is required for cross-runtime compatibility — do not copy files from agents/ or commands/ directly.

On another runtime or without Node.js? See Install on your runtime.

Once installed, start your first project:

/gsd-new-project

New here? Follow Your first project for a guided walkthrough from install to first shipped phase.

---

[!NOTE] This is a Jujutsu fork of GSD.

If you're viewing this repository you're probably looking to use Jujutsu (jj) with GSD. Once you install this fork:

1. Run jj git init --colocate in your project (if you don't already have a .jj/ directory).
2. Run /gsd-migrate-vcs in your harness of choice — it migrates your existing plans to reference jj change ids instead of git commit ids.

If you're not migrating an existing GSD project to jj, then simply make sure to jj git init before you run /gsd-new-project, and GSD should pick up and use the Jujutsu backend automatically.

After that, all GSD features should work roughly as expected. If you find any bugs, please open an issue or pull request against this fork.

[!WARNING] You should make sure to always be on an empty revision before running GSD operations. GSD expects to squash changes down selectively, as that is how subagents work in-place. This allows you to work within history rather than only at the head of a branch, as long as it has an empty change to effectively use as the head.

---

Documentation

Tutorials — learning by doing:

• Your first project
• Onboarding an existing codebase

How-to guides — task-focused recipes:

• Install on your runtime
• Plan a phase
• Verify and ship
• … see all how-to guides

Reference — authoritative facts:

• Commands
• Configuration
• CLI tools

Explanation — concepts and design decisions:

• Context engineering
• The phase loop
• Architecture