2bc53baa03
* test(#2947): milestone anchor must prefer heading with Phase details Row 1 of the test matrix: the failing-first regression test. When the phase-listing heading (## Phases) is NOT version-bearing but a later version-bearing progress heading (### v9.0 phase progress) exists, extractCurrentMilestone latches onto the progress heading and silently drops the phases (phase_count: 0, exit 0). Five cases: the regression, the version-bearing control (must keep working), the no-phase-details fallback, the closed-vs-open preference, and an end-to-end roadmap.analyze check. Reproduced locally against built lib + confirmed by maintainer triage (trek-e). The one-word control (## Phases -> ## v9.0 Phases) restores phase_count: 2. * fix(#2947): preserve preamble phase details when the milestone section has none Root cause was one layer deeper than the issue title: the anchor selection (selected = first non-closed version-bearing heading) is fine — the real drop happens in the preamble strip. When the phase list lives under a non-version-bearing ## Phases heading (the shipped greenfield template's own shape) and the selected version-bearing heading is a LATER progress/notes sub-heading with no ### Phase N: details of its own, the preamble strip removed every phase-detail heading from the pre-milestone region (intended to avoid duplication with a Phase Details section that does not exist here) — silently dropping all phases (phase_count: 0, exit 0, empty stderr). Fix: only strip preamble ### Phase N: headings when the selected milestone section (currentSection) actually contains its own phase details. When it does not, the preamble phases ARE this milestone's phases and must be preserved. Falls back to today's behavior (strip) whenever the selected section has phase details, so multi-milestone roadmaps with a dedicated Phase Details section (#730) are unaffected. Surgical: one conditional on the existing strip, no signature change, no change to computeSectionEnd or the #730 Phase Details append. Blast radius CRITICAL (84 upstream symbols) — the change is gated on currentSection's content so every existing roadmap that currently resolves phases correctly keeps doing so byte-identically. * chore(#2947): add changeset fragment * chore(#2947): backfill changeset PR number 3084 --------- Co-authored-by: sim <sim@local>
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.