cc0a4685f1
An isolated review found the safety precondition was not safe. Test 4 uses the repo's own tests/ directory as a path that must never be deleted, and asserted beforehand that it sits outside the temp root — but it computed that root as path.resolve(os.tmpdir()) alone, while cleanup() accepts a target under any of several root spellings. For a checkout under the realpath'd temp root the precondition reads "outside, safe to proceed" while the guard reads "inside, delete it", and rmSync runs on tests/ before the assertion fails. The commit that added it claimed it would fail loudly instead of destructively; it would have done the opposite. The fix is not a second root in the test. tmpRootCandidates() is exported and the precondition calls it, so there is one source of truth and nothing left to drift. A mirror was the defect, not its contents. The same review bounded what the refusal actually guarantees: the check is a string prefix test, so a symlink living under tmpdir but pointing outside it passes while rmSync follows the link and deletes the real directory. When the target exists its real path is now checked too, against the same predicate — factored into one function so the two comparisons cannot diverge the way the test's copy did. A realpath failure refuses rather than proceeds; a safety check that cannot verify must not report safe, which is the whole subject of this branch. Missing targets are skipped, since rmSync with force no-ops on them and realpathSync would only throw ENOENT. `const isTmpPath = true` is gone. It survived the previous commit as a way to keep the catch's `&& isTmpPath` reading as a real condition, but a constant dressed as a test states nothing; the guard clauses above throw, so the catch comment now says the invariant in words instead. The new coverage does not depend on the platform the bug lives on. The root list is asserted directly — non-empty, absolute, deduped, and containing a freshly created temp dir — and the symlink refusal runs everywhere, skipping only where symlink creation is unavailable. The previous realpath test was coverage-identical to the control on Linux, so the only lanes the matrix runs could not have verified the fix it was written for. Refs #3057 Co-Authored-By: Claude Opus 5 <noreply@anthropic.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.