b2d50ffd83
* fix(#4489): make capability-registry.test.cjs's extractShellBlocks CRLF-safe Second, independent copy of the #4409 CRLF-fragile line-splitting bug, explicitly flagged as out of scope there ("other duplicated helper in file sibling test files not part of the shadowing chain, tracked separately if divergent"). Same fix: content.split('\n') -> content.split(/\r?\n/), matching src/text-lines.cts's splitLines() and the already-fixed sibling copy in tests/runtime-launcher-parity.test.cjs. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * chore(#4488): regenerate INVENTORY-MANIFEST.json for tdd-red-evidence.cjs's ADR-457 untracking Discovered while validating #4489's push: #4488's merge (untracking gsd-core/bin/lib/tdd-red-evidence.cjs per ADR-457) left docs/INVENTORY- MANIFEST.json stale, since that file was previously listed as a tracked shipped artifact. Removed via node scripts/gen-inventory-manifest.cjs --write. docs/INVENTORY.md already described this file as gitignored (no update needed there -- it already documented the intended state). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> * revert: undo incorrect INVENTORY-MANIFEST.json edit from 57f1457a27 The prior commit removed tdd-red-evidence.cjs's manifest entry based on a false premise: a stale tsconfig.build.tsbuildinfo (gitignored, untouched by git checkout/rebase) told tsc the file's compilation was already current even though git's own checkout had deleted the actual output file during this branch's rebase onto #4488's merge (a tracked-in-old-tree, untracked-in-new-tree transition deletes the working-tree file regardless of the new .gitignore entry). tsc's incremental cache doesn't verify its recorded output still exists on disk, so it silently skipped re-emitting it. Confirmed real root cause: deleting tsconfig.build.tsbuildinfo and rebuilding fresh correctly re-emits gsd-core/bin/lib/tdd-red-evidence.cjs (it is gitignored now, not deleted -- src/tdd-red-evidence.cts is unaffected by ADR-457's tracked-vs-gitignored distinction and always compiles). The manifest's own purpose (per its docstring) is 'every shipped surface derived entirely from the filesystem' -- this file still ships via the normal build, so it belongs in the manifest regardless of git-tracking status. Net result matches next's own INVENTORY-MANIFEST.json byte-for-byte; this correction should not have been needed at all had the build cache been fresh when the prior commit was made. 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.