Joe Slitzker ee6f3b70c5 fix(#1477): write .gsd-source marker at install; resolve install-exports for the deployed layout
The Claude Code global skills layout ships gsd-core/{bin,contexts,references,
templates,workflows} but not the commands/gsd source tree, and
_runLegacyUninstallCleanup removes any commands/gsd/ for that scope. So at
runtime findInstallSourceRoot's walk-up from gsd-core/bin/lib has nothing to
find and /gsd-surface throws for every subcommand (list/status included). The
marker reader added in #1476 never fired because nothing wrote the marker.

Writer half (Failure 1): install() writes <configDir>/.gsd-source pointing at
the package's commands/gsd source (guarded on its presence so a half-published
package never leaves a dangling marker). findInstallSourceRoot already prefers
this marker over the walk-up.

Deployed install-exports (Failure 2): loadInstallExports' relative
'../../../bin/install.js' only resolves in the repo; in a deployed tree it
points at <configDir>/bin/install.js, which is never shipped, so the surface
write subcommands threw MODULE_NOT_FOUND. Derive install.js from the resolved
commands/gsd source root instead (its package root holds both commands/gsd and
bin/install.js), which is correct in the repo (walk-up) and in deployed installs
(marker) alike. No file relocation needed, so install.js' own internal requires
keep resolving. applySurface threads layout.configDir so the marker is honored.

Regression test reproduces the deployed global layout end-to-end: without the
marker the deployed walk-up throws, and getInstallExports under the old relative
path throws MODULE_NOT_FOUND; with both fixes list/status resolve and the
install-exports load. Adversarial marker cases (dangling, empty/whitespace)
fall through to walk-up.

Claude-Session: https://claude.ai/code/session_01XNT3SWgzjmEycNuweURDme
2026-06-20 09:15:59 -05:00

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, Gemini CLI, Kimi CLI, Kilo, Codex, Copilot, Cursor, Windsurf, and more.

npm version npm downloads Tests Discord GitHub stars License


What is GSD Core

GSD Core is a context-engineering and spec-driven development framework that drives AI coding agents (Claude Code, Codex, Gemini 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:

  1. Discuss — capture implementation decisions before anything is planned
  2. Plan — research, decompose, and verify the plan fits a fresh context window
  3. Execute — run plans in parallel waves; each executor starts with a clean 200k-token context
  4. Verify — walk through what was built; diagnose and fix before declaring done
  5. 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, Gemini 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 your first project:

/gsd-new-project

New here? Follow Your first project for a guided walkthrough from install to first shipped phase.


Documentation

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

Star History Chart

License

MIT License. See LICENSE for details.


Claude Code is powerful. GSD Core makes it reliable.

Description
No description provided
Readme MIT 77 MiB
Languages
JavaScript 82.3%
TypeScript 17.4%
Shell 0.3%