6e681cb36c
* test(#3901): the guard suite must survive a developer's global core.hooksPath (failing first) * fix(#3901): the commit-docs-guard suite isolates children from the host git config A developer's GLOBAL core.hooksPath (~/.gitconfig) applies to every fresh repo, so the guard's correct refusal — it will not install a hook git would never run — failed this suite's beforeEach and 18 tests read as a commit-docs-guard regression on any machine that centralizes commit hooks. CI never saw it (runners have no global git config). before() pins GIT_CONFIG_GLOBAL to an empty file for the whole suite (runGsdTools and the git helpers propagate process.env to every child). A LOCAL repo value cannot isolate this: any non-empty local value trips the same refusal, and an empty local value makes rev-parse --git-path hooks resolve to ./ instead of .git/hooks. The regression test pins the seam: the isolation file is armed and empty, a child git resolves no hooksPath from the host, and the beforeEach enable installed the hook at the repo-local default path. A child given an explicitly hostile GIT_CONFIG_GLOBAL still refuses — that is the guard being correct. * fix(#3901): review fold-ins — isolation hoisted to all three guard suites; changeset Adversarial review: the pin covered suite A only — the B (#3588 B1-B15) and D (real git commit wiring) suites run enable against fresh repos too and failed identically on hostile-global machines; the issue's 18 failures could not have come from A's five tests alone. The pin is extracted to isolateGlobalGitConfig() and armed in all three suites (B9's LOCAL hooksPath test is unaffected — the pin neutralizes only the global scope; D's premise is the hook firing from .git/hooks, which the isolation preserves). * chore(#3901): backfill changeset PR number (4063) * fix(#3901): drop the now-unused before import — max-warnings 0 fails CI --------- 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.