c70e736c85
Unrelated defect surfaced by a real gsd-test failure while verifying #3339 (test/3339-fold-state-model-profile diffs zero files this fix touches -- confirmed via `git diff <this-branch> origin/next -- ...` returning empty for this file, ship.md, and gsd-core/bin/lib/*.cjs). Fixed inline per this repo's no-defer policy for defects found while building, rather than deferred. The test's jq() mock shelled out to a full new Node.js process for every mocked `jq -r .field` call inside the extracted track_shipping bash script. The "exhausts the polling bound" test hits up to 24 cold Node spawns in one spawnSync call (6 polling iterations x 4 jq calls), racing a hardcoded 10s timeout -- under CI contention this tipped over on the linux-node22 lane specifically while linux-node24 had headroom, producing spawnSync's signal-killed `status: null` instead of the process's real exit code, asserted against the expected 0. Replaced the Node-subprocess jq() mock with a pure-shell sed -nE field extractor that never forks a process, eliminating the variable-cost operation rather than just widening the timeout. Verified extraction correctness against sample JSON (head/status/checks/review, including empty-string and non-matching-field cases). Locally verified (scoped per session policy): all 9 tests in the file pass; the previously- marginal test dropped from ~617ms to ~198ms. The underlying track_shipping polling logic in ship.md was confirmed correct and untouched -- this was a test-fixture race, not a product bug.
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.