The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Phase-loop system for Claude Code and other agents
GSD Core gives AI coding agents a repeatable workflow for shipping work in phases. It combines prompts, agent files, state documents, and verification steps so planning, execution, and review stay structured across sessions. The loop is designed to keep the main conversation lean while subagents do the heavier work in fresh context.
Builders who want their agent sessions to stay organized, reviewable, and less prone to context drift.
You can ship work in smaller, verifiable phases without re-explaining the project every session.
What it does
Five-step phase loop
Runs work through discuss, plan, execute, verify, and ship so each phase follows the same structure.
Fresh-context subagents
Moves research, planning, and execution into new subagent contexts to reduce context rot.
Persistent project state
Uses files like `STATE.md` and `CONTEXT.md` so the project carries forward between sessions.
Cross-runtime installer
Installs through a runtime-aware setup instead of copying files by hand.
Verification before ship
Includes a verify step that checks the work and produces fixes before a phase is marked done.
Multi-runtime support
Works across Claude Code, Codex, Cursor, Windsurf, Copilot, and other agent runtimes.
How to get it
- 1Run
npx @opengsd/gsd-core@latest
- 2Once installed, start a new project or onboard an existing repo
/gsd-new-project # greenfield project /gsd-onboard # existing codebase
README
GSD Core
Git. Ship. Done.
English · Português · 简体中文 · 日本語 · 한국어
A light-weight meta-prompting, context engineering, and spec-driven development system for Claude Code, OpenCode, Antigravity CLI, Kimi CLI, Kilo, Codex, Copilot, Cursor, Windsurf, and more.
What is GSD Core
GSD Core is a context-engineering and spec-driven development framework that drives AI coding agents (Claude Code, Codex, Antigravity CLI, Kimi 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:
- Discuss — capture implementation decisions before anything is planned
- Plan — research, decompose, and verify the plan fits a fresh context window
- Execute — run plans in parallel waves; each executor starts with a clean 200k-token context
- Verify — walk through what was built; diagnose and fix before declaring done
- 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, Antigravity CLI, Kimi 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 a new project or onboard an existing repo:
/gsd-new-project # greenfield project
/gsd-onboard # existing codebase
New here? Follow Your first project for a guided walkthrough from install to first shipped phase, or Onboarding an existing codebase for brownfield setup.
Documentation
What's new in 1.7.0 → docs/whats-new-1.7.0.md
Tutorials — learning by doing:
How-to guides — task-focused recipes:
Reference — authoritative facts:
Explanation — concepts and design decisions:
Full index: docs/README.md. Other languages: 日本語 · 한국어 · Português · 简体中文.
Why it works
Most AI-coding setups fail at scale because context bloat silently degrades output quality, there is no shared memory between sessions, and nothing verifies that code actually works. GSD Core solves all three: heavy work runs in fresh subagents, structured artifacts like STATE.md and CONTEXT.md survive session boundaries, and the verify step walks through what was built and generates fix plans before a phase is declared done. See docs/explanation/context-engineering.md for the full reasoning.
Troubleshooting? See docs/how-to/recover-and-troubleshoot.md.
Community
| Project | Platform |
|---|---|
| gsd-opencode | Original OpenCode port |
| Discord | Community support |
Star History
License
MIT License. See LICENSE for details.
Claude Code is powerful. GSD Core makes it reliable.
Files in the repo
- .changeset
- .claude-plugin
- .githooks
- .github
- .gsd
- .kilo
- .opencode
- .out-of-scope
- .plans
- agents
- assets
- bin
- capabilities
- commands
- docs
- eslint-rules
- examples
- gsd-core
- hooks
- pi
- scripts
- skills
- src
- tests
- vscode
- .base64scanignore
- .clinerules
- .coderabbit.yaml
- .editorconfig
- .gitattributes
- .gitignore
- .nvmrc
- .pr-body-2100.md
- .pr-body-3514.md
- .pr-body-3515.md
- .release-monitor.sh
- .secretscanignore
- CHANGELOG.md
- CONTEXT.md
- CONTRIBUTING.md
- eslint.config.mjs
- GEMINI.md
- LICENSE
- package-lock.json
- package.json
- README.ja-JP.md
- README.ko-KR.md
- README.md
- README.pt-BR.md
- README.zh-CN.md
- SECURITY.md
- stryker.config.mjs
- TEST-EXAMPLES.md
- TESTING-STANDARDS.md
- tsconfig.build.json
- tsconfig.json
- VERSIONING.md
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More harnesses
from vibe coding to agentic engineering - practice makes claude perfect
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

The most RAM efficient harness
A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents