44ddc6dc46
* test(#3865): init.* phase queries accept --phase as positional alias (failing first) * fix(#3865): init.* phase queries accept --phase <N> as the positional alias The phase-taking init.* queries read their phase token at args[2] blindly: '--phase 60' made the literal '--phase' the phase, which the locator can never resolve — the reported incident answered a well-formed phase_found:false, plan_count:0 with exit 0 for a phase holding seven committed plans (ADR-3473 §8.4's later strict validation turned the paired form into a usage error instead, still not the alias). normalizePhaseAlias (shared by all eight phase-taking handlers — the issue's four plus phase-op, review, discuss-phase-assumptions, todos, the same class) rewrites '--phase N'/'--phase=N' into the caller-owned positional slot before flag parsing, so handlers and strict validation see exactly the argv the positional form produces. A valueless --phase is a usage error naming the flag. Any other flag-shaped args[2] now resolves to undefined (the commands' designed use-the-current-phase input) instead of passing flag text down as a phase name. isFlagToken exported from command-arg-projection (single owner of the flag-shape predicate). * fix(#3865): review fold-ins — honest no-position-given comment, fail-closed throws The helper's comment claimed flag-shaped args[2] resolves to 'the commands' designed use-the-current-phase input' — no such cross-module behavior exists: execute-phase/plan-phase/verify-work usage-error 'phase required', the find-based queries answer phase_found:false, and todos drops its area filter. Reworded to what actually happens, so the contract-grade comment cannot mislead a future edit. Adds the parseNamedArgsOrExit-style throw after each error() call as a fail-closed backstop against a returning fail(). * chore(#3865): changeset fragment (pr number backfilled after PR creation) * chore(#3865): backfill changeset PR number (4054) --------- 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.