itsvedantkumar/vstack

5 stars · Last commit 2026-09-05

A Claude Code setup where the skills fire on their own: situation-routed skills, subagents, a session routing hook, and a verification gate whose every check is mutation-proven falsifiable. Installs global, per-repo overlay, or plugin marketplace.

README preview

# vstack

**A Claude Code configuration bundle whose every claim is checked by something that can fail.**

[![verify](https://github.com/itsvedantkumar/vstack/actions/workflows/verify.yml/badge.svg)](https://github.com/itsvedantkumar/vstack/actions/workflows/verify.yml)
[![release](https://img.shields.io/github/v/tag/itsvedantkumar/vstack?label=release&color=6f42c1)](https://github.com/itsvedantkumar/vstack/releases)
[![license](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
[![plugin](https://img.shields.io/badge/claude%20plugin-vstack-6f42c1.svg)](#install)
[![runs on](https://img.shields.io/badge/runs%20on-macOS%20%2B%20Linux-lightgrey.svg)](#limits)

vstack installs skills, subagents, commands and hooks into Claude Code, and a gate that stops an
agent reporting a task done while the tests are red. It is for people who run agents unattended
and need to know afterwards which parts actually held.

## What it gives you

What the install adds, stated as mechanisms you can read rather than promises.
Each names a file on disk and, where it makes a claim, a check that can fail.

**A gate that refuses a false "done."** `goal-gate.sh` on Stop will not let an agent end a turn

View full repository on GitHub →