dc9b299b4e
* test(#2359): failing-first regression for the 1.4.0 Cursor commands citation The `## [1.4.0]` CHANGELOG entry for the `.cursor/commands/` surface carries the trailing reference (#803) — the Cline PR, cited correctly by the entry two lines below. The Cursor surface shipped in #805 (feat(#785)). Adds four behavioral cases to the owning module's test file, asserting through parseChangelog (the same parser cmdExtract/cmdVerify/cmdRender use) rather than raw text matching: 1. the Cursor bullet cites 805 - FAILS before the fix 2. the adjacent Cline bullet still cites 803 - guards a global s/803/805/ 3. exactly one Cursor bullet exists - guards drop/duplicate 4. the two bullets cite different PRs - the defect as an invariant Folded into tests/changeset-serialize.test.cjs rather than a new bug-2359-*.test.cjs file, per scripts/lint-regression-test-names.cjs. Refs #2359 * fix(#2359): CHANGELOG 1.4.0 Cursor commands entry cites #805, not #803 The `## [1.4.0]` entry for `gsd install --cursor` writing `.cursor/commands/gsd-<name>.md` carried the trailing reference (#803). That PR is `feat(#787): elevate Cline` — cited correctly by the entry two lines below. The Cursor slash-command surface shipped in #805 (`feat(#785): write .cursor/commands/ Cursor 1.6 slash-command surface`). Two adjacent bullets therefore claimed one PR, and only the second was right. The trailing (#NNNN) is machine-parsed by parseChangelog and consumed by `changeset extract`, so the wrong number is live data, not only prose — and it had already propagated to a human reporter (#2341, quoted there as "#785 / #803"). Single-occurrence, line-anchored edit. The Cline entry's (#803) is correct and is deliberately untouched; the regression test added in the preceding commit asserts both, so a global s/803/805/ fails. Prose is unchanged, including the "both surfaces are written on every install" clause the issue explicitly certifies as accurate. Fixes #2359 * chore(#2359): changeset fragment for the Cursor commands citation fix * test(#2359): assert bullet cardinality before reading it Review findings, one root cause: each of the four cases re-derived the bullet list, re-filtered by marker, then destructured `const [x] = ...` and read `.pr` unguarded. A reworded or deleted entry therefore died with TypeError: Cannot read properties of undefined (reading 'pr') instead of naming what was missing. The repetition was also duplicated logic across all four cases. Adds locateBullet(version, marker, label), which asserts exactly one match before returning, and folds the two cardinality guards into one case covering both entries. Failure mode verified: a marker matching nothing now raises AssertionError "expected exactly one bogus bullet in the 1.4.0 section, found 0". Refs #2359 * chore(#2359): backfill changeset pr number (#3252) --------- Co-authored-by: sim <sim@local>
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.