59da9f016b
* fix(#4466): bound quick.md's post-execute review scope tip at the task's own last commit The review-scoping step computed CHANGED_FILES as `git diff --name-only "${DIFF_BASE}..HEAD"`. DIFF_BASE is correctly bound to the quick task's start (via the oldest QUICK_COMMITS entry's parent), but the tip was bare HEAD -- unbounded. Anything landing on the shared tree between the task's own commits and this review step running (a worktree merge-back, another session sharing the tree) got folded into the quick task's own review scope. QUICK_COMMITS (newest-first) already holds the correct tip as its first line -- read QUICK_TIP from the value already computed, diff against that instead of HEAD. No new derivation, no new git call. Added tests/quick-review-scope-tip-bound.test.cjs: extracts the scoping fence verbatim from quick.md and runs it against a real git fixture matching the issue's own scenario (quick task's own commit, then a later unrelated commit on the shared tree). Manually verified watch-it-fail (bare HEAD includes the unrelated file) / watch-it-pass (bounded tip excludes it) via direct bash execution before wiring the test file, since this repo blocks local node --test. Independent code review caught one drive-by finding: an allow-test-rule marker copied from a sibling test's pattern was unnecessary here (and there) -- local/no-source-grep's looksLikeSourcePath only matches readFileSync targets ending in .cjs/.cts/.js/.mjs/.mts/.ts, never .md, so the rule can never fire regardless of the marker. Confirmed by reading eslint-rules/no-source-grep.cjs directly; removed. Emitted-Drift-Ack-Growth: quick.md — the fix adds a QUICK_TIP line and its explanatory comment; not a regeneration artifact, a hand-authored bug fix. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * docs(#4466): 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.