0062f6d033
next went red on dacae9273 against documentation that was correct.
parseDeclaredCounts read any '<numeral> ... dimensions' collocation as a claim
about the gsd-ui-checker dimension TOTAL. The how-to sentence 'Dimension 7 is a
rule gsd-ui-checker follows, the same as the other six dimensions' refers to the
other members of a seven-member set; the guard counted it as that document
declaring six, and reported a count-mismatch on prose that was accurate. A drift
guard that fires on correct prose is a false positive, which is how guards end
up switched off.
A negative lookbehind now excludes a numeral introduced by 'other' or
'remaining'. It is declared once as NOT_A_BACK_REFERENCE and shared by both
English scans rather than written at each site — the same two-surface divergence
class this suite exists to catch. Both scans apply it case-insensitively; the
first cut of this fix had the digit scan case-sensitive and the word scan not,
so a sentence-initial 'Other 6 dimensions' still slipped through. The exclusion
is word-anchored, so 'another six dimensions' — a real claim about a second set
— still counts.
parseDeclaredCounts takes an excludeBackReferences opt-out so a test can prove
against the REAL shipped how-to that the exclusion is load-bearing: with it off
the file reports [6,7], with it on [7]. That replaces a raw substring match on
prose, which the suite's own header forbids, with a typed before/after.
The docs prose is deliberately unchanged. It is the only instance of the pattern
in the tree, so keeping it means the real-tree assertion exercises the path this
fix exists for instead of asserting only on fixtures.
Regression tests cover both polarities: eight back-reference shapes including
all four sentence-initial cases, five real count claims that must still count,
the 'another' word-boundary case, and the shipped how-to itself.
Known limits recorded in the code: the exclusion is English-only, because
translated docs here are corrected to match English rather than authored, so
there is no instance to model the grammar on; and it cannot distinguish a
back-reference from a genuine total opening with the same word ('Other 6
dimensions were added'), where the false negative is the safer side of the trade.
Why it reached next at all: the docs PR (#3746) was green. A doc-only diff
inert-skips the test matrix in the PR lane, so the guard that reads docs never
ran against the docs change that broke it — it fired on push to next, after
merge.
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.