* fix(#4469): anchor beginPhaseCore's focusPattern regex to line start focusPattern (src/state-transition.cts, beginPhaseCore's first-time- execution branch) rewrites the **Current focus:** body line via a regex with no line anchor and \s* (crosses newlines) instead of a same-line whitespace class -- the same defect class already fixed for a different function, stateReplaceField, in #4243/PR #4453. A bold **Current focus:** quoted mid-sentence anywhere in the body (e.g. an Accumulated Context bullet documenting the field) matched first and had the rest of its line silently overwritten with the new focus label -- the #4010 data-loss class, applied to a different field. Anchored using the exact same idiom PR #4453 established: ^([ \t]*\*\*Current focus:\*\*[ \t]*)(.*)$ with the /m flag. [ \t]* (not \s*) avoids consuming the newlines before the label into the match; $ documents the match ends at end-of-line. Added a regression test to tests/state-transition.test.cjs: a body with NO real **Current focus:** field yet present, but a mid-sentence prose mention of the same bold text in an Accumulated Context bullet -- proving the unanchored pattern would corrupt the prose (empirically verified via direct node -e execution before wiring the test) while the anchored pattern's .test() correctly returns false and leaves it untouched. stateReplaceProgressPercent's bold branch (~line 51-71) is explicitly NOT touched -- the issue itself flags it as entangled with the recorded #2177 form-priority decision, needing a maintainer call. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * docs(#4469): backfill changeset PR number Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> --------- Co-authored-by: sim <sim@local> Co-authored-by: Claude Sonnet 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.