c1a2c33886
My instrumentation suite tipped ubuntu shard 1/3 over its 15-minute job cap.
Measured, not guessed: baseline on next (c8f08b61f) passed that shard in
14m21s — 39 seconds of headroom — and the chunk-timeout instrumentation suite
I added costs 31,621ms, about 80% of what was left. The job ran 15m09s and
GitHub reported the cap as a cancel, which failed the required-tests rollup.
Cause is spawn count, not test content. The suite booted scripts/run-tests.cjs
five separate times — three success-path, two timeout-path — and each boot
globs the suite and spawns node --test children before any assertion runs. The
direct-require tests beside it cost milliseconds.
Now two spawns: one success run backing the elapsed-timing, temp-dir-non-leak
and no-EINVAL assertions, and one timeout run backing the in-flight-file
naming and the diagnostic wording. Every assertion is kept verbatim; only the
per-assertion subprocess boot is gone. Modelling per-boot overhead from the
measured total puts the saving around 18s, but that is an estimate derived
from one data point, not a measurement — the real number comes from CI.
The chunk timeout stays at 2000ms. It is already the lowest value used
anywhere in this file, and lowering it further would race a loaded CI box that
has to boot node --test, register the hang, and observe the kill inside the
window.
Worth recording separately: that lane has 39 seconds of margin on next, so it
is one cliff away from this happening to whoever adds the next test. The
per-chunk timing this PR adds is what made the attribution possible at all —
chunk 1/5 alone is 263s of a 900s budget, which was previously invisible.
Verification runs on the remote runner.
Refs #4012
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.