19fa7364e0
* test(#2199): cover bullet/em-dash ROADMAP phase resolution + milestone count Adds the bullet-only ROADMAP fixture the suite lacked: an all-bullet em-dash ROADMAP resolves each phase (no Phase null), colon/en-dash/hyphen bullet separators all resolve, mixed heading + bullet forms coexist, and the milestone phase-count counts bullet-form phases instead of collapsing to zero. * fix(#2199): accept bullet/em-dash phase entries in roadmap lookup + milestone filter Roadmap phase lookup (findRoadmapPhaseInContent) matched only ATX headings against a colon-required pattern, so a bullet/checkbox entry like `- [ ] **Phase N — name**` — which the bundled roadmapper emits in bullet-house- style ROADMAPs — resolved found:false and `Phase null` was written into STATE.md. The milestone phase-filter built its phase set from headings only, so a bullet- only ROADMAP collapsed to a zero-count pass-all filter and progress denominators broke. - Add a shared bullet-phase-line pattern (separator: em-dash/en-dash/hyphen/colon). - findRoadmapPhaseInContent: on a heading-match miss, fall back to the bullet line for the requested phase; return found:true with the captured name. - getMilestonePhaseFilter: also scan bullet lines into the milestone phase set. Closes #2199 * docs(#2199): add changeset fragment * fix(#2199): bullet phase lookup as last resort + consolidate test (review) Two corrections to the initial fix: 1. Regression — the bullet fallback inside findRoadmapPhaseInContent was too eager: it returned a bullet match from the scoped (current-milestone) content before the caller tried the full-content heading path, so a phase whose Requirements live in a Phase Details heading (after the active-milestone section) got a bullet-line section with no Requirements → phase_req_ids null (broke 3 init tests). Restructure: findRoadmapPhaseInContent is heading-only again; a separate findRoadmapBulletPhaseInContent runs in getRoadmapPhaseInternal ONLY after scoped + full heading lookup fails, so a heading with a Requirements section always wins. 2. lint-test-file-count — the standalone fix-2199-roadmap-bullet-phase.test.cjs collided with the over-cap 'roadmap' module (FAIL_NOVEL_FILES). Consolidate the regression into the existing tests/roadmap-parser.test.cjs (its natural home, under the 2-file cap). * test(#2199): assert heading-in-full beats bullet-in-scoped (review L3) The exact first-attempt regression: a phase has a bullet in the active-milestone scope but its heading (carrying Requirements) lives in a Phase Details section outside that scope. Pin that the heading section wins over the bullet line so req_ids resolve and the eager-bullet bug cannot return. * docs(#2199): backfill PR number in changeset fragment
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
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.