0f3959516c
* fix(#4106): drop the orphaned test:mutation:since script `"test:mutation:since": "stryker run --incremental --since origin/next"` could not run. Stryker has no `--since` flag — verified against the pinned `@stryker-mutator/core` 9.6.1, whose options schema has no `since` property and whose CLI exits `error: unknown option '--since'`. It went unnoticed because nothing invokes it. `.github/workflows/mutation.yml` uses the per-module matrix instead: `scripts/mutation-matrix.cjs` computes the changed covered modules and each shard runs its own `npx stryker run --incremental --mutate "${MUTATE_GLOB}"`. That path works, so no gate ever exercised the script. It is still worth removing rather than leaving: its name makes it the obvious thing to reach for when a reviewer asks for a mutation score on changed scope, and the Commander parse error it produces says nothing about the matrix being the real entry point — the next person has to reverse-engineer mutation.yml to find that out. Delete rather than repoint. The issue offered both, and the maintainer had not picked; delete is the option that stays scoped to the reported bug. The suggested replacement (`node scripts/mutation-matrix.cjs --base origin/next`) emits a CI matrix rather than running mutants, so shipping it under a `test:mutation:*` name would be a second, differently-shaped claim, and documenting the per-module invocation in CONTRIBUTING.md is enhancement-shaped work that belongs in its own issue. The discovery command is named in the changeset instead. Flipping this PR to the pointer script is a one-line change if that is preferred. The regression test asserts that every `stryker` script in package.json passes only flags Stryker's own options schema defines. It carries its own control — the historical `--incremental --since origin/next` string is checked to still be rejected by the same predicate — so the sweep cannot go quietly vacuous if the remaining invocations lose their flags. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017zgWzB96uz3LVKdJePYTLR * chore(#4106): backfill the changeset PR number Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017zgWzB96uz3LVKdJePYTLR * docs(#4106): mark the changeset docs-exempt `type: Removed` makes docs-lint require a `docs/` change. Nothing under `docs/` or in CONTRIBUTING.md ever referenced `test:mutation:since` — the script was orphaned and could not run — so there is no documented behaviour to update. Using the gate's own per-fragment escape hatch rather than weakening the changeset type to dodge the requirement. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017zgWzB96uz3LVKdJePYTLR --------- Co-authored-by: Claude Opus 5 <noreply@anthropic.com> Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
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.