fd64389616
* test(#2703): failing-first coverage for CRLF frontmatter strip in SUMMARY.md Drives the exported buildPlanningArtifacts seam. Rows for CRLF/LF parity, stacked blocks and a leading BOM fail against the current hand-rolled regex; the negative-space rows pin behavior that must not change. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(#2703): strip GSD-2 frontmatter with the canonical parser buildSummaryMd matched the closing delimiter with a hardcoded bare \n, so a CRLF-authored task summary never matched and fell through to the raw-passthrough branch. The function then prepended its own block, emitting a SUMMARY.md with two stacked frontmatter blocks and no warning. Delegates to stripFrontmatter from frontmatter.cts -- the canonical, line-ending tolerant primitive this repo already deduplicated once (#2143) -- instead of adding another hand-rolled variant. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(#2703): strip only the first frontmatter block in gsd2 import Adversarial review caught a regression in the first cut: stripFrontmatter loops by design, so a summary body opening with a thematic-break-delimited section (--- / heading / ---) had that section silently deleted. The old pre-#2703 regex preserved it, so shipping the loop would have traded one silent corruption for another. Adds an explicit { once } option to the canonical primitive -- default behavior and the two existing callers are unchanged -- and has buildSummaryMd opt in. A GSD-2 summary is an arbitrary user document, not a GSD artifact with a known doubling failure mode, so a second block there is body content. This also makes the acceptance criterion exact: CRLF now produces the same result LF already produced, rather than a new result for both. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * chore(#2703): backfill changeset pr number Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- 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.