04ac8723b9
* test(#4024): pin quantitative-criteria trap shapes for verify plan-structure Rows 1-3 and 20 of the #4024 test matrix reproduce the issue's shapes (exact grep -c counts, bulk all-N observed-failing claims) and are expected to FAIL against unmodified next: nothing judges these shapes today. Corrected-arm rows pin that each rule is silent on its own fix. * fix(#4024): flag quantitative-criteria trap shapes in verify plan-structure Add scanQuantitativeCriteria, the third plan-discipline scanner in the cmdVerifyPlanStructure family (#429, #968). It judges criteria text in <acceptance_criteria>/<automated>/<verify> blocks against a six-rule ban list of shapes proven to be traps at HEAD: exact grep -c counts (R1), bulk all-N observed-failing claims (R2), unquoted $VAR in command position (R3), fallible git swallowed by a non-final pipeline stage (R4, warn), wc output compared by string equality (R5), and relative HEAD~N git anchors (R6; bare git diff warns). Legitimate exit: <!-- plan-criteria-allow: R# - reason -->. Pure text scan, fail open. * test(#4024): bind node:test before hook locally below the fold-point * fix(#4024): R3 command-position anchor tolerates list bullets and inline-code backticks * test(#4024): bind VERIFY_CJS locally in the unit block instead of relying on fold scope * fix(#4024): R6 argument span ends at inline-code backtick or redirection * fix(#4024): satisfy no-adhoc-markdown lint on the R4 stage-boundary regex * chore(#4024): add changeset fragment * chore(#4024): backfill PR number in changeset fragment * fix(#4024): escape backticks in regex literals so drift-lint tokenizers keep function attribution --------- 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.