c9dd4aa951
* test(#2940): prove gsd-update discards codex config after the GSD marker Failing-first regression for #2940. mergeCodexConfig Case 2 (marker present) preserves content before the marker but discards everything from the marker to EOF, so user/Codex-CLI settings ([model], [mcp_servers.*], [profiles.*]) added after a fresh install are wiped on every update. Rows 1-2 assert trailing user content survives; rows 3-7 cover idempotency, the #2406 leaked-section non-regression, the [agents] namespace, both regions, and the zero-trailing boundary. * fix(#2940): preserve codex config.toml content after the GSD marker on update mergeCodexConfig Case 2 (marker present) preserved content before the marker but discarded everything from the marker to EOF, so user/Codex-CLI settings added after a fresh install ([model], [mcp_servers.*], [profiles.*]) were wiped on every gsd-update. Route the trailing region through the existing stripLeakedGsdCodexSections, which removes GSD's own managed/leaked sections (the bare [agents] table GSD regenerates, legacy [agents.gsd-*], [[agents]]) while preserving genuine user TOML. The marker comment line (and the optional codex_hooks ownership line) is stripped from the trailing region first so it is not duplicated alongside the regenerated block. #2406's de-dup still holds (leaked sections after the marker are still stripped), and re-merge is idempotent. * fix(#2940): use CRLF-safe regex in regression test (lint:ci no-crlf-fragile-split) The Row 7 blank-line assertion used a bare \n which trips local/no-crlf-fragile-split under Windows git-autocrlf. Use \r?\n. * fix(#2940): correct Row 5 to valid single-[agents] TOML shape The isolated adversarial review found Row 5 (bareAgentsAfterMarkerHandled) constructed TWO [agents] tables (the GSD-managed one + a user trailing one), which is invalid TOML — a duplicate table definition. extractCodexUserAgentsScalars reads only the first [agents] and stripLeakedGsdCodexSections removes ALL bare [agents] tables, so the user's max_threads would be silently dropped. The valid, realistic shape is the user folding max_threads INTO the managed [agents] block (which the existing spliceCodexAgentsScalars path preserves) plus a separate trailing [model]. Reword Row 5 to that shape. A duplicate-[agents] input is invalid TOML Codex itself rejects, so it is out of scope for this fix. * chore(#2940): add changeset fragment * chore(#2940): backfill changeset PR number 3067 --------- 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.