fad5094587
Replaces the timing-dependent execFileSync(timeout:5000) approach with a spawnSync-based runHook that tests the scanner's RESULT (exit code + output shape), never how long it takes. Root design flaw in the prior approach: execFileSync's timeout (5000ms) was identical to the scanner's own internal setTimeout(5000ms), creating a non-repeatable race (F.I.R.S.T. violation: not Repeatable). Under concurrent test-chunk load — which #2089's 3 new cursor test files redistribute — node22's event-loop scheduling let execFileSync's SIGTERM win the race, producing err.status=null → exitCode=1 → spurious property-test failure. Redesign (F.I.R.S.T.): - spawnSync (not execFileSync): non-zero exits return a result object, not an exception — cleaner for property tests - Non-serializable payloads (BigInt, circular refs, Symbol) are SKIPPED: the scanner receives JSON via stdin, so these values are outside its protocol — JSON.stringify throwing is a test-harness artifact, not a scanner defect - 30s safety-net timeout is NOT a test assertion: scanner exits in <100ms; 30s only catches a genuinely hung process (6x the scanner's own 5s internal timer → no race possible) - Assertions check exit===0 and output structure, never timing qa-test-architect pipeline: risk=HIGH (security boundary); automation= subprocess (real shipped hook); test-cases cover happy/boundary/negative/ independence; verified via gsd-test.
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
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.