#7070th of 85 in Skills, plugins and rules

gsd-core

Spec-driven phase loop that runs AI coding agents in fresh-context subagents

Stars: 10.3k
License: MIT
Last commit: Oct 2026
Last release: Oct 2026
Language: JavaScript

Missed the latest GitHub check; these facts may be older.

Overview

GSD Core installs commands and agents into coding runtimes such as Claude Code, Codex, Cursor, Copilot and Windsurf. It drives each milestone through a discuss, plan, execute, verify, ship loop, running research and execution in fresh-context subagents to limit context rot. State persists between sessions in files like STATE.md and CONTEXT.md.

Who it is for: Developers using AI coding agents who want a structured, spec-driven workflow

Strengths

One installer targets many runtimes, including Claude Code, Codex, Cursor, Copilot, OpenCode and Kimi CLI
Persists project state in STATE.md and CONTEXT.md across sessions
Verify step walks through built work and generates fix plans before a phase closes
Docs split into tutorials, how-to guides, reference and explanation

Weaknesses

Must be installed through its installer; copying agents/ or commands/ files directly is unsupported
Fixed five-step phase loop imposes a workflow on every project
Default install path uses npx, so it needs Node.js; other runtimes need a separate guide
README gives no benchmarks for its context-rot claims

What it needs

no GPU
Needs Node.js, npm
Models: Claude Code, Codex, OpenCode, Antigravity CLI, Kimi CLI

Also in Skills, plugins and rules

See all 85

Also in Skills, plugins and rules
Rank	Project	Score
1	skillsAgent skills for planning, TDD, debugging and code review291.3k starsMIT	94 out of 100
2	eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses279.5k starsMIT	94 out of 100
3	cavemanCuts token use in coding agents with terse replies and compressed inputs Live demo ↗ (opens in a new tab)111.9k starsApache-2.0	94 out of 100
#4	ponytailSkill prompt that makes coding agents write less code and add tests163.6k starsMIT	92 out of 100
#5	impeccableDesign skill with 24 commands and a detector for AI-generated frontends Live demo ↗ (opens in a new tab)81.2k starsApache-2.0	92 out of 100

How to choose

Check which agent it targets and whether it works with the version you run.
Read what it adds to every prompt; big rule sets cost tokens on each call.
Prefer add-ons you can turn off per project.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

MIT Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the copyright and license notice in copies you ship.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#70 of 85 in Skills, plugins and rules on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/open-gsd/gsd-core.svg)](https://archestack.com/best-of-vibe-coding/projects/gsd-core/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/gsd-core/" title="gsd-core on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with gsd-core filled in.