dad16b6ef9
* fix(#4141): ignore Stryker's sandbox in eslint's global ignores `stryker.config.mjs` sets `tempDirName: '.stryker-tmp'`, `.gitignore` ignores it, and Stryker's own always-ignored list carries it. eslint's global `ignores` did not, and there is no `.eslintignore`. A mutation run that dies before cleanup — chunk timeout, CI cancellation, Ctrl+C, a crash — leaves a full sandbox copy of the tree at `.stryker-tmp/sandbox-*/`, and `npm run lint` then lints the copy. The failure is not the duplicate-file failure that would suggest, which is what makes it confusing: the `local` plugin is registered only in path-scoped config blocks (`tests/**/*.cjs`, `scripts/**/*.cjs`, `hooks/**`), and a copy at `.stryker-tmp/sandbox-*/tests/*.cjs` matches none of them, so every inline `// eslint-disable-next-line local/<rule>` the original carries becomes `Definition for rule 'local/<rule>' was not found` at the copy's path. The error text names rules rather than paths, so the first read is "my change broke the local plugin" — observed as 834 errors on a branch whose own diff was clean, from a sandbox eight days stale. CI never sees this (fresh checkout), so it is purely a local-contributor tax, but a loud and misleading one. The regression test asserts the invariant the way ESLint resolves it — `isPathIgnored()` over real flat-config precedence, not a textual scan of the ignores array — mirroring the #551 block it sits beside, and carries the control that the real `tests/worktree.test.cjs` at the mirrored path is still linted, so a pattern widened enough to swallow the tree cannot pass. Scoped to the reported bug: `reports/` may deserve the same treatment, but no lint failure has been reproduced from it, so it is not claimed here. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017zgWzB96uz3LVKdJePYTLR * chore(#4141): backfill the changeset PR number Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017zgWzB96uz3LVKdJePYTLR * chore(#4141): restore the file's 2-blank-line block separator Review nit: the #4141 block left three blank lines before the RETIRED block, where every other block boundary in this file uses two. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Mw7WhYnrWdY8cmj8NSJj4R --------- 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.