From a0593e81a5dd7946e76ec52cc4fc85f1c7f1bc26 Mon Sep 17 00:00:00 2001 From: Spencer Date: Thu, 26 Mar 2026 20:48:14 -0500 Subject: [PATCH] docs: add new machine setup instructions to README --- README.md | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 2d08484..2317188 100644 --- a/README.md +++ b/README.md @@ -14,7 +14,21 @@ Everything is plain text [by design](https://lab.puga.com.br/cog/#/why-text). No Cog is a learning tool — an experiment in watching how a memory architecture evolves when given clear conventions and self-observation capabilities. You set the rules, Claude scaffolds the structure, and the pipeline skills refine the conventions over time. The model doesn't evolve — it follows whatever rules it finds. The rules are what change. Every decision is visible. Every rule is editable. Every change is in the git log. -## Quick Start +## Setting Up on a New Machine + +Clone the repo and hand `BOOTSTRAP.md` to Claude Code — it will handle the rest: + +```bash +git clone https://gitea.bunny-wyvern.ts.net/artanis/Cog-Sync.git /home/artanis/.cog +``` + +Then open Claude Code anywhere and say: + +> Read `/home/artanis/.cog/BOOTSTRAP.md` and set up Cog on this machine. + +Claude will symlink `CLAUDE.md` globally, wire up the skills, and verify the install. Takes about a minute. + +## Quick Start (fresh install from template) Requires [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview).