b0f1722662
* test(#2969): completed_plans must ratchet up for gap-closure plans Failing-first regression: when deriveProgressKeys=true (cmdStatePlannedPhase's opt-in), applyStatePreservation restores completed_plans to its pre-growth curated value, so gap-closure plans that complete never increment it — STATE.md shows completed_plans < total_plans forever even though every PLAN has a SUMMARY. Three cases: the ratchet-up (derived 54 > curated 50), the ratchet-down protection (derived 47 < curated 50 keeps curated), and the body-only write protection (no deriveProgressKeys → wholesale restore). The existing #2440 test covers the case where derived < curated (ratchet holds); this adds the missing case where derived > curated (ratchet must release upward). * fix(#2969): ratchet completed_plans/plases up under deriveProgressKeys applyStatePreservation's deriveProgressKeys path (cmdStatePlannedPhase's opt-in) let total_plans/total_phases take the derived value but restored completed_plans/completed_phases to their pre-growth curated value — so gap-closure plans that completed after the plan count grew never incremented them, leaving STATE.md at completed_plans < total_plans forever (every PLAN had a SUMMARY). Extend the deriveProgressKeys exclusion to also let completed_plans and completed_phases take the derived value, but ratcheted UP only (never derive downward past curated) — preserving the #3242 curated-progress protection for cases unrelated to plan-count growth (e.g. a deleted SUMMARY). percent takes the derived value (the resync already recomputed it from disk counts). Scoped to deriveProgressKeys (plan-phase only); body-only writes (state.update/patch without the flag) keep the full #3242 wholesale restore. * fix(#2969): also take derived percent under deriveProgressKeys Isolated-review blocker: percent fell into the else branch and was overwritten with the stale curated value, contradicting the inline comment and leaving STATE.md incoherent (e.g. completed_plans:54/total_plans:54 at percent:93). Skip percent in the ratchet loop so the derived (resync- recomputed) value survives. * chore(#2969): add changeset fragment * chore(#2969): backfill changeset PR number 3091 --------- Co-authored-by: sim <sim@local>
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.