249c586a40
The guard added in #3656 asserts that this test leaves the real repo hooks/ directory alone. It compared a RAW listing before and after — and just failed on the runner: the real repo hooks/ directory listing must be unchanged by this test - '.dist-staging-20858', 'dist', ... Nothing was wrong with the test's own behaviour. A CONCURRENT scripts/build-hooks.js — nine test files invoke it from before() hooks — created hooks/.dist-staging-20858 inside the comparison window. The assertion assumed the shared hooks/ directory is stable for the duration of a test, which is precisely the assumption this line of work exists to disprove. The race-detector raced. The intent is right and is kept: this test must not add or remove anything in the repo. Only the comparison changes — both snapshots are now filtered through shouldCopyHookEntry, the same rule the fixture itself uses, so transient build scratch that is not this test's doing and is excluded from the fixture anyway no longer registers as a difference. Proven by execution: with a .dist-staging dir injected mid-window the filtered listings compare equal, while the unfiltered listings provably differ by exactly that entry — so the old comparison would have failed and the new one is immune rather than merely quieter. The injected directory is removed afterwards and hooks/ is confirmed byte-identical. Checked for the same shape elsewhere: this is the only raw listing comparison of the live hooks/ directory in the file or the repo. The second title in the failure output is the describe() wrapper around this same test, not a sibling. Refs #3582 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.