fdac556746
* fix(#1160): resolve capability surface from installed skill layouts In a global skills-runtime install (e.g. Codex at ~/.codex), gsd-tools.cjs runs from <configDir>/gsd-core/bin/ and the commands/gsd source tree is absent — only <configDir>/skills/gsd-<stem>/SKILL.md files exist. _resolveCommandsGsdDir() returned a path that does not exist there, so loadSkillsManifest returned an empty Map. resolveSurface then materialised the '*' (full) profile sentinel by enumerating that empty manifest → empty surfaced Set → every capability reported surfaced=false/enabled=false regardless of project config. As a result `loop render-hooks verify:post` returned activeHooks:[] even with workflow.security_enforcement and workflow.nyquist_validation enabled, silently disabling the security and Nyquist gates. Fix: add _loadInstalledSkillsManifest(configDir) that scans configDir/skills/ for gsd-<stem>/SKILL.md dirs and builds the same Map shape, and _resolveManifest(commandsGsdDir, configDir) that prefers the source tree when present (preserving repo-checkout behaviour) and falls back to the installed skills layout otherwise. Both resolveCapabilityRuntimeState call sites use _resolveManifest. Both helpers are exported for direct unit-testing. Tests: capability-state.test.cjs gains a faithful installed-runtime e2e block that copies gsd-core/bin + scripts + package.json into a temp install root with no reachable commands/gsd, then runs the real gsd-tools.cjs against an installed skills/ layout. It asserts capability state reports security & nyquist enabled and verify:post includes security->secure-phase and nyquist->validate-phase; a disabled-config negative confirms no over-activation. This block FAILS before the fix (activeHooks:[]) and PASSES after. Plus unit coverage for the two new helpers and the empty-surface pre-fix scenario. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(changeset): backfill PR number Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.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, Gemini 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, Gemini 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, Gemini 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 your first project:
/gsd-new-project
New here? Follow Your first project for a guided walkthrough from install to first shipped phase.
Documentation
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.