d91e32b3ce
* fix(#2383): untrack node_modules — accidentally committed as a hardcoded absolute-path symlinkcf004df67(#2360/#2364) swept node_modules into git as a tracked 120000 (symlink) blob pointing at /Users/trekkie/projects/gsd-core/node_modules — a path specific to one contributor's machine. .gitignore already lists node_modules/, so this was almost certainly a broad `git add` run while node_modules happened to be a symlink at that path, not intentional (git add on an explicitly-added path isn't blocked by .gitignore). Two concrete problems this caused: (1) anyone else cloning the repo, or any CI runner, checks out a symlink pointing at a path that does not exist on their machine; (2) it silently self-heals for most people (npm ci detects the checked-out symlink is "not a directory" and replaces it), but anyone who runs a tool directly against node_modules/.bin/* before ever running npm ci hits ENOENT/ELOOP failures that read as environment corruption and are expensive to diagnose — exactly what happened while preparing PR #2380 before this tracked entry was found to be the actual root cause. git rm --cached only, no working-tree content touched. .gitignore already covers node_modules/ going forward; confirmed via `git showcf004df67--stat` that no other file was swept into that same commit by the same mistake. Closes #2383 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#2383): gitignore node_modules regardless of file type node_modules/ (trailing slash) only matches directories, so it never suppressed the worktree-sharing symlink some worktrees use to point node_modules back at the main checkout — every such worktree showed a perpetual, un-ignorable "?? node_modules" in git status, exactly the noise that trains people to stop reading git status output. Dropping the trailing slash matches node_modules regardless of whether it's a real directory, a file, or a symlink, which is what every other repo's node_modules ignore rule actually needs to do. Found while directly verifying #2383's untrack fix was complete, not assumed. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * chore: regenerate cursor golden-install-parity fixture after rebase next advanced again during rebase — #2386 (fix #2341, "de-dup Cursor menu by marking skills user-invocable:false") landed and legitimately changed every cursor SKILL.md's content. Confirmed via git log that this is the explanation before committing: all 71 changed hash entries are isolated to cursor.json, matching a runtime-specific skill-output change, not noise. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix: regenerate cursor golden fixture from a clean clone (worktree was stale) Local worktree regeneration didn't match CI's clean-room result despite multiple attempts; a fresh clone + npm ci + regenerate in isolation produced a different, correct result. Using that. --------- Co-authored-by: Claude Opus 4.8 <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.