17bf25a3d2
* docs(#4671): lock the config-resolution and CLI-encoding design
Amend ADR-1411 in place with the design contract for epic #4633: one
per-key resolution owner that returns the producing layer, two declared
configuration families with no precedence invented between them, one
parser and one encoder at the config-get boundary, a round-trip property
scoped to what raw output can actually carry, and the migration census,
child boundaries and anti-divergence guard spec.
Every claim about current behaviour was reproduced on next at c9a5cc3e1
in a hermetic fixture. Two corrections to the epic's framing: #4382 is
not a separate double-encoding defect (a present array already emits a
real JSON array — its own repro uses --default, the same defect as
#4262), and --default is already correct under --raw, so the disagreement
is confined to the JSON arm.
Docs-only. No runtime code, configuration behaviour or generated
artifact changes; every absorbed symptom stays live until the code
children land.
Closes #4671
* docs(#4671): close the migration-census gap and rule Decision 4
Review found the Decision-5 census missing model-resolver.cts's
projectExplicitlySetsOmit() (a workstream->root precedence walk, same
class as the six listed Family A implementations) and flagged init.cts's
readConfigJsonBoolean/readConfigJsonValue as a plausible second gap
(single-layer reads, same class as the listed single-layer readers).
Verified init.cts directly: confirmed real, added.
Decision 4 asked for an explicit maintainer ruling on raw-mode losslessness.
Ruled: freeze --raw as documented (display/shell-interpolation contract,
lossy for non-scalars). A lossless --raw stays out of scope, its own
future issue.
* docs(#4671): qualify config resolution guarantees
Distinguish correct classification from precedence guarantees and freeze raw as lossy output.
---------
Co-authored-by: Tom Boucher <trekkie@nomorestars.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.