Tom Boucher 8c79044298 fix(#384): make getAgentsDir runtime-aware so non-Claude installs find agents (#617)
* fix(#384): make getAgentsDir runtime-aware so non-Claude installs find agents

getAgentsDir() ignored the active runtime and always returned the
claude-family __dirname-relative agents path, so on OpenCode (and other
non-Claude runtimes) checkAgentsInstalled() looked in the wrong directory
and reported agents missing even when installed. Resolve the per-runtime
global config dir via getGlobalConfigDir(runtime) (GSD_AGENTS_DIR env >
runtime arg > GSD_RUNTIME env > 'claude'), and surface agent_runtime and
agents_dir through withProjectRoot() so init diagnostics show which
directory was checked. Updates the stale W010 health-check test that
relied on the old __dirname path.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* chore(#384): set changeset pr to 617

* fix(#384): keep claude on __dirname agents path; fix test lint + leak

Address CI failures on the first cut:
- getAgentsDir now only routes NON-claude runtimes through
  getGlobalConfigDir(runtime); claude retains the original __dirname-
  relative agents path, which correctly resolves to <repo>/agents for
  repo runs and the runtime config agents dir for real installs. This
  restores validate-health / W010 checks that were regressing because the
  claude default had moved off the repo-relative path.
- Revert the now-unneeded GSD_AGENTS_DIR workaround in
  agent-install-validation.test.cjs (back to its next state).
- bug-384 test: use helpers.cleanup() instead of raw fs.rmSync()
  (local/no-raw-rmsync-in-tests) and drop an unused var.
- Reword a doc comment that contained a literal ~/.claude/agents path,
  which tripped the cline-install no-leaked-paths scanner.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 16:14:33 -04:00
2026-05-15 18:16:33 -04:00

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, 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, 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, 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 79 MiB
Languages
JavaScript 82.2%
TypeScript 17.4%
Shell 0.4%