137f3115a1
* fix(#4492): index the suffix window instead of pattern-matching it `MSG_SUFFIX="${CMD#*"$MSG_MATCH"}"` is quadratic in the -m message. bash tries every prefix length and compares the whole matched literal at each, and MSG_MATCH is BASH_REMATCH[0] — the entire `-m "..."` — so the cost grows with the thing being scanned. Measured on the real hook: 10.0s at 64KB, 22.0s at 96KB, 30.2s at 112KB, 40.1s at 128KB. `bash -x` with an EPOCHREALTIME PS4 attributes 10.116s of a 10.2s run to that one expansion, which computes an empty string. Conforming and non-conforming cost the same, so this is the path every commit takes, and Claude Code blocks on PreToolUse hooks. MSG_PREFIX on the line above has already located the match, so the suffix is arithmetic rather than a search. Same first-occurrence assumption both expansions always made — MSG_MATCH is a literal substring of CMD by construction. Equivalence checked across 480 comparisons on bash 3.2.57 and 5.3.15 under C, UTF-8 and SJIS locales, including multibyte text, repeated matches, metacharacters and invalid bytes. Three regression rows, all deliberately on the RESOLVE=1 path so they pin the suffix scan alone and do not depend on the separate #4429 SIGPIPE fix: non-conforming and conforming 112KB heredocs, plus a suffix-window row whose padding sits before the heredoc opener's newline so the COMMAND is large while the message stays small. Red against the true base — all three killed at the 10s bound with the head -1 sites still present — and green with only this change. Fixture sizes stay under Linux MAX_ARG_STRLEN (131072 on a 4KB-page kernel). Above it execve fails, the classifier cannot launch and the hook fails open, so a larger fixture measures the argument limit rather than the suffix scan; an earlier 131225-byte draft passed on base AND head for exactly that reason. Every row asserts empty stderr, which is what separates "validated" from "failed open". The bound is enforced by killing the process GROUP, not the direct child: the hook spawns a node classifier that inherits stdout, so killing only bash can leave the pipe open and `close` never arrives. `local/no-elapsed-assertion` forbids asserting on elapsed time, and `{ timeout }` is inert on a synchronous body, so the rows are async and the kill is the signal. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01UZw5UhR474YLyE4knjHrte * chore(#4492): add changeset Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01UZw5UhR474YLyE4knjHrte --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
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.