a65cb291e8
* test(#4105): guard the #3889 hang fixture — must genuinely hang by itself and self-terminate RED at this sha: against the current never-settling-promise body the guard fails on the matrix line (Node 24: the unheld promise never self-terminates, ceiling expires) and off it (v22-class runtimes: the child exits rc=1 after ~60ms, never reaching the still-hanging checkpoint). Same shape as the #4104 self-exit regression: spawn the exact served body, observe liveness past the chunk bound and natural exit — no elapsed-value assertions. * fix(#4105): park the #3889 hang fixture on a settling timer The never-settling promise held no libuv handle, so the hang T1/T4 rely on was a property of the runtime's test-runner shutdown behavior, not of the fixture: v24/v26 happen to hold the loop open; v22-class runtimes exit rc=1 after ~60ms (# cancelled 1), so the chunk never reaches the timeout path and the two timeout assertions assert nothing. Park on a settling 10s timer (the #4104 idiom): an explicit handle makes the hang the fixture's on every Node line, 10s >> the 2000ms chunk bound (margin asserted structurally in the #4105 guard), ~0% CPU while parked, and guaranteed self-termination if a kill orphans it. Behavior on the Node 24 matrix line is unchanged — the chunk is still killed by the harness timeout (~2006ms) with the identical diagnostic. * test(#4105): drive the fixture guard off the child's exit event + runner timeout Review-driven restructure (Memtrace flaky_test_fixed_sleep on the 200ms poll interval): the guard now waits on the child's natural 'exit' event — no polling interval, no hand-rolled watchdog setTimeout. The immortal-body bound is the node:test per-test { timeout: 2 * HANG_PARK_MS } backstop, the health-validation #663 house pattern and the no-elapsed-assertion-compliant form. t.after still reaps the child on every path. Same failing-first arms: still-hanging checkpoint, natural-exit (no signal), exit code 0. * changeset(#4105) * changeset(#4105): backfill PR number --------- 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.