Tom Boucher 5214ad5802 fix(#4267): correct tdd.md pointer citations; fix(#4269): collapse plan-level gate-rule duplication (#4295)
* fix(#4267): correct tdd.md pointer citations; fix(#4269): collapse plan-level gate-rule duplication

execute-plan.md and gsd-executor.md each cited "Red-Green-Refactor Cycle"
for three facts (commit-scope contract, fail-fast rule, error handling),
but only the commit-scope contract lives there. Fail-fast is in tdd.md's
"Fail-Fast Rules" subsection (under "Gate Enforcement Rules") and error
handling is in tdd.md's "Error Handling" section — cite each correctly.

gsd-executor.md's "Plan-Level TDD Gate Enforcement" section also fully
restated the gate-sequence rules tdd.md's "Gate Enforcement Rules" already
owns (and covers more thoroughly, including the actual git-log validation
script). Collapse it to a short pointer, matching the treatment already
used by the cycle-steps pointer immediately above it.

Adds tests/tdd-reference-correctness.test.cjs asserting the pointer text
cites the correct section names, that those sections actually carry the
guidance, and that the old gate-sequence restatement is gone from
gsd-executor.md.

Closes #4267
Closes #4269

* docs(#4267): add changeset for tdd.md pointer correctness fix

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* chore(#4267): acknowledge execute-plan.md growth

execute-plan.md grew 95 bytes (39766 -> 39861) from the corrected
three-section citation in the #3990/#4267 cycle-steps pointer.

Emitted-Drift-Ack-Growth: execute-plan.md — net +95 bytes from citing the "Fail-Fast Rules" and "Error Handling" sections by name instead of a single mis-scoped section (#4267).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* fix(#4267): update PROSE_ALLOWLIST line numbers shifted by the pointer-citation edit

This branch's edits to agents/gsd-executor.md and gsd-core/workflows/execute-plan.md
shifted line numbers, leaving tests/no-bare-gsd-tools-command-position.test.cjs's
PROSE_ALLOWLIST pointing at stale lines. Update both entries to their new correct
lines (811 and 419 respectively) without changing the underlying prose.

* fix(#4267): restore INVALID_RED citation, fix allowlist line shift after #3770 rebase

The rebase onto next picked up #3770's already-merged fail-fast update to
gsd-executor.md's plan-level gate section, which this branch's own commit
collapses into a pointer. The conflict resolution kept the pointer but
dropped the literal "INVALID_RED" term that tests/tdd-red-evidence.test.cjs
requires gsd-executor.md to name — restored it. Also updates
no-bare-gsd-tools-command-position.test.cjs's PROSE_ALLOWLIST line number
for gsd-executor.md, shifted again by the rebase.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* test(#4267): fix non-matching regression-guard regex in tdd-reference-correctness

The fail-fast regression guard asserted gsd-executor.md no longer contains
"If a test passes unexpectedly during the RED phase" — but the actual old
prose (removed by this branch's pointer-collapse) read "If a test passes
unexpectedly during RED, STOP". The regex never matched the real old text,
so the assertion would have passed even against the unmodified pre-change
file. Caught by an isolated orthogonal review pass. Fixed to match the
actual removed wording, and confirmed (via a direct grep) it is genuinely
absent from the current file.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* docs(#4267): backfill changeset PR number

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

---------

Co-authored-by: sim <sim@local>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-04 19:13:56 -04:00
2026-08-30 02:40:59 +00:00
2026-08-30 02:40:59 +00:00

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.

npm version npm downloads Tests Discord GitHub stars License


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:

  1. Discuss — capture implementation decisions before anything is planned
  2. Plan — research, decompose, and verify the plan fits a fresh context window
  3. Execute — run plans in parallel waves; each executor starts with a clean 200k-token context
  4. Verify — walk through what was built; diagnose and fix before declaring done
  5. 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

Star History Chart

License

MIT License. See LICENSE for details.


Claude Code is powerful. GSD Core makes it reliable.

Description
No description provided
Readme MIT 77 MiB
Languages
JavaScript 82.3%
TypeScript 17.4%
Shell 0.3%