c9d3e66631
* fix(#4341): reference-count the git-config sandbox the three guard suites share node:test evaluates every describe body during collection, before any test runs, so the three isolateGlobalGitConfig() calls happened back to back and each captured the PREVIOUS call's temp path as its "original": A captured undefined, B captured A's path, D captured B's. Suite A's after() fires first and restored undefined — deleting GIT_CONFIG_GLOBAL outright — so suites B and D ran against the developer's real ~/.gitconfig for the rest of the file. A also cleanup()'d a directory B still pointed at. One sandbox now, with the true original captured once and released when the last holder lets go; each returned restorer is idempotent, so an extra call cannot release someone else's hold. The three call sites are unchanged. Reproduced with a global core.hooksPath (via a fixture HOME carrying a .gitconfig, so the developer's real one is never touched): next: ℹ pass 291 ℹ fail 7 — "core.hooksPath is set to ...; a hook written to .../pre-commit would never run" branch: ℹ pass 296 ℹ fail 3 The 3 that remain are two suites (pr-subrepo, #3776 query commit --files) that never called isolateGlobalGitConfig at all — the same class, a different gap, and outside this issue's scope. Noted on the PR. D0 is the regression guard and is deterministic on every lane: suite A's after() runs before this suite's tests, so on the old helper GIT_CONFIG_GLOBAL is already gone by then regardless of what the host's git config contains — which is what makes it fail on CI, where the core.hooksPath that exposed the defect is absent. Verified: full-file run reds on the old helper, greens on the new one. * test(#4341): clean filtered gitconfig sandboxes on exit * test(#4341): retain exit cleanup until release succeeds
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.