4048ba2e80
* test(#3860): quick-tasks heading tolerance for milestone suffixes (failing first) * fix(#3860): prefix-match Quick Tasks heading + schema-aware section selection The exact-anchored predicate (^quick tasks completed$) never matched a milestone-suffixed heading ('Quick Tasks Completed (v1.1+)'), so every /gsd-fast append AND every reset failed with QUICK_TASKS_SECTION_ABSENT before the columns were ever looked at — the reported table was already canonical. A heading is a section label, not data: the predicate is now prefix-anchored with a word boundary (Completedness still excluded), hoisted to one shared isQuickTasksHeading beside QUICK_TASKS_SECTION_ABSENT so the two call sites cannot drift. Section selection is now schema-aware (the issue's deliberate-choice ask): among ALL matching sections, the first whose table parses with a recognized Quick Tasks schema wins — a legacy (v1.0) table first in document order no longer shadows a usable (v1.1+) one below it. When no section is usable, the FIRST is returned so the error names the real problem (unrecognized schema) instead of a false 'no section'. Fixes one over-assertion in the new tests (v1.1+'s own next ordinal IS 2; pins v1.0 rows byte-identical instead). * fix(#3860): review fold-ins — level-bounded bodies, splice guard, convention pin Adversarial review caught that collectSections ends a candidate's body only at the next MATCHING heading: an intervening '## Deferred Items' table (canonical STATE.md layout — templates/state.md puts it after the Quick Tasks section) would be swallowed into the body, and the append's last-table-line scan would splice the quick-task row into that WRONG table — silent corruption on the primary /gsd-fast path. Each candidate is now re-collected through collectSection with an offset-precise predicate, restoring the pre-#3860 level-bounded stop (next same-or- higher heading) for both probing and splicing. Also pins the both-schema-valid tie-break (document order, newest-on-top — the layout the issue itself demonstrates; this layer has no active-milestone signal) with a test, guards the Deferred Items layout with a dedicated splice-target test, and updates resetQuickTaskRows's doc comment to name the new pipeline. * chore(#3860): changeset fragment (pr number backfilled after PR creation) * chore(#3860): backfill changeset PR number (4050) --------- 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.