ba26aa065d
* docs(#4467): document fallow's structural-pre-pass has no upper-bound scope structural-pre-pass.md's FALLOW_SCOPE_ARGS=(--changed-since "$FALLOW_BASE") derives a correct, phase-anchored LOWER bound (lockstep with Tier 3's own scope step, #3995), but fallow's --changed-since is one-sided by design -- verified against fallow 2.70.0's own --help: the only other scoping flags are --changed-workspaces (workspace selection, not a file range) and --diff-file (its own help text scopes it to line-range refinement within the hot-path-touched verdict, not general file selection; gsd-core never uses it). Reviewing an earlier phase after a later one has landed pulls the later phase's files into the earlier phase's structural audit. Not fixable inside this file: fixing fallow itself is a third-party concern, and working around it (e.g. auditing from a temporary worktree checked out at the phase tip) is disproportionate machinery for what is supplementary structural-analysis context, not a blocking gate -- both routes the issue's own analysis already ruled out. Documented the asymmetry at the point the scope is derived instead, so a future reader does not assume this step's tip agrees with Tier 3's just because the base does. No regression test: documentation-only, no runtime behavior change. A prior revision of this commit carried an Emitted-Drift-Ack-Growth trailer for this growth -- gsd-test's own emitted-attribution check rejected it as stale ("written or reworded in THIS diff, but nothing here needed them"), meaning this file (nested under gsd-core/workflows/code-review/steps/, unlike a top-level gsd-core/workflows/*.md file) is not tracked by that specific growth conservation law. Removed the now-confirmed-unnecessary trailer rather than guess again -- the test's own verdict is authoritative here, not a re-derivation of its tracked-path rules. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * docs(#4467): backfill changeset PR number Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> --------- Co-authored-by: sim <sim@local> Co-authored-by: Claude Sonnet 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.