9723d2b7e0
Nine assertions drove a real fault through a real seam and then checked only that the call did not throw, or that a result was a string, a boolean, an array. Each passed whether the code was right or wrong. #3050 is the canonical instance of the shape: its counter-test asserted effectiveRoot was a string and never which root, so a silent misroute passed it. All nine now assert the exact verdict, derived from the production branch each one reaches and traced back to source rather than taken from the survey. One was worse than a weak assertion. The test targeting resolveWorktreeLinkage's main_worktree path used createTempGitProject, which always seeds .planning/ — so the reason was always has_local_planning and the git-dir comparison the test appears to exercise was unreachable from its own fixture. It was not asserting loosely, it was pointed at the wrong path. The fixture now builds a git project without .planning (projectDoc had to be disabled too, since it defaults to git and would have re-seeded it), and the test reaches the branch it names. Another had no reason assertion anywhere in the file while its four siblings all pinned theirs — the odd one out rather than a convention. The last is mine. The parity guard shipped in #3077 checked typeof and doesNotThrow across four ExecGitFn seams, and that PR described it as failing "the moment any site re-grows its own shape". It could not: a site returning a different value of the same type passed it. All four benign-passthrough outputs are derivable exact values, so it now asserts them and the claim is true. Test names that promised more than their assertions established are corrected to match what they prove. Refs #3057 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
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.