4f6fda852e
* fix(#1591): phase.complete recognizes checkbox-list phases in the isLastPhase fallback When the active milestone's phase checklist is written as `- [ ] Phase N:` checkbox items inside a <details> block (the @Azd325 structure) and the next phase has no directory yet, the disk-based next-phase resolver finds nothing and phase.complete falls back to the roadmap-enumeration guard at the isLastPhase site. That guard's phasePattern was heading-only (/#{2,4}\s*Phase…/), so it never matched checklist items → is_last_phase=true and next_phase=null on a mid-milestone phase, and STATE.md was wrongly marked 'Milestone complete' with total_phases decremented. Broaden the marker alternation to match BOTH heading-style (### Phase N:) and checkbox-list items (- [ ] Phase N: / - [x] Phase N:); the number/name captures are unchanged. extractCurrentMilestone already surfaces the <details>-wrapped checklist correctly, so no parser change is needed. The heading-only sibling patterns elsewhere in phase.cts are left untouched (scope discipline — only the reproduced isLastPhase fallback is changed). Regression: a phase complete 36 on a <details>-wrapped v2.0 checklist (Phases 36-38, only 36 has a dir) returns is_last_phase=false, next_phase=37, and does NOT flip STATE.md to 'Milestone complete'. * docs(#1591): add changeset fragment for phase.complete checkbox-list fix * test(#1752): add total_phases-preservation regression for the #1591 follow-up #1752 is the scoped follow-up to #1591 — same <details>-wrapped-checkbox defect, with the additional emphasis on the total_phases decrement cascade. The #1591 fix (is_last_phase=false) already resolves it: with all 8 phase dirs on disk, phase.complete 36 on a v2.0 <details> checklist leaves total_phases at 8 (not decremented to 7) and does not flip STATE.md to 'Milestone complete'. Verified manually before adding the test. Add the #1752 regression case (8 phase dirs, curated total_phases: 8) to the phase complete command block in tests/phase.test.cjs, and update the changeset to reference both issues (#1591, #1752) since this is one user-facing change resolving both.
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, Gemini 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, Gemini 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, Gemini 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 your first project:
/gsd-new-project
New here? Follow Your first project for a guided walkthrough from install to first shipped phase.
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.