# open-gsd/gsd-core

Git. Ship. Done - Core

Repository: https://github.com/open-gsd/gsd-core
Canonical: https://ross.abutalabs.com/products/gsd-core
Homepage: https://opengsd.net
Language: JavaScript
License: MIT
License Family: permissive
Topics: claude-code, context-engineering, meta-prompting, spec-driven-development
Last push: 2026-08-26T23:43:51+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 7
- inputs: {"age_days": 103, "days_push": 7, "days_rel": 14, "gap_med": 3, "n_releases_24m": 20}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8756, forks 621 (observed 2026-08-28T04:10:25.516408+00:00)

## What it is
GSD Core is a meta-prompting, context-engineering, and spec-driven development framework that orchestrates AI coding agents (Claude Code, Codex, Cursor, Copilot, and others) through a disciplined Discuss-Plan-Execute-Verify-Ship phase loop. It combats context rot by running research, planning, and execution in fresh-context subagents while keeping the main session lean.

## Use cases
- run spec-driven development with AI coding agents
- prevent context rot in long AI coding sessions
- orchestrate parallel AI executor subagents with clean contexts
- structure AI-assisted milestones from plan to pull request
- onboard an existing codebase for AI-driven development
- install a workflow engine across multiple AI coding runtimes

## When to choose
- you already use Claude Code, Cursor, Codex, Copilot, or a similar AI coding runtime and want a structured workflow on top
- your AI agent sessions degrade as the context window fills
- you want explicit plans, verification gates, and git-truthful history for agentic work
- you need cross-runtime compatibility for AI coding workflows

## When to avoid
- you want a standalone autonomous coding agent rather than a workflow layer (consider GSD Pi)
- you don't use AI coding agents at all
- you need a lightweight single-prompt helper rather than a full phase-loop methodology

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, prompt-engineering, workflow-automation, developer-tools, cli
- domain: developer-tools, large-language-models
- platform: cli, cross-platform
- tags: spec-driven-development, context-engineering, meta-prompting, claude-code, ai-coding-agents, subagents, slash-commands, ai-agents, automation, nodejs

## Member repositories
- open-gsd/gsd-core (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:25.516408+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:25:15.644026+00:00, confidence not recorded.
  - readme: https://github.com/open-gsd/gsd-core (fetched 2026-08-28T04:10:25.516408+00:00, sha aa26ebe799fb)
  - homepage: https://opengsd.net (fetched 2026-08-29T08:25:49.415867+00:00, sha 6a3d62c2e153)
  - site_page: https://opengsd.net/about (fetched 2026-08-29T08:25:49.418764+00:00, sha 144a7a1e7c7d)
  - site_page: https://docs.opengsd.net/ (fetched 2026-08-29T08:25:49.420967+00:00, sha 8f105de4f56a)
  - site_page: https://opengsd.net/docs (fetched 2026-08-29T08:25:49.423365+00:00, sha 485bf4dcd655)
- Data as of 2026-08-30T08:39:29.467469+00:00.