Most Claude Code setups are minimal. Mine is not.
After weeks of real projects, I open sourced the exact config I use daily.
What's inside:
CLAUDE.md with commit format, PR format, branch naming, and coding rules Claude actually follows
Per-project memory via Obsidian. Claude reads PROJECT, MISTAKES, and CONTRACT files at session start so it never forgets context
84% token savings with RTK, Headroom, and claude-mem
Karpathy coding principles baked in
One command setup: bash setup.sh ~/your-vault
Works with any stack.
janmaaarc
/
basecamp
A production-ready Claude Code setup. Global CLAUDE.md, coding rules, per-project memory, and token optimization.
basecamp
A production-ready Claude Code setup. Global CLAUDE.md, coding rules, per-project memory, and token optimization.
Quick Start
git clone https://github.com/janmaaarc/basecamp.git
cd basecamp
bash setup.sh ~/Documents/your-vault
Then open ~/.claude/CLAUDE.md, fill in your stack, and follow Setup for tools and plugins.
What This Is
This is the exact setup I use daily. Not a template made for show. A working system built and refined through real projects.
Most Claude Code setups are minimal. This one is not. It covers:
- Global instructions Claude follows on every project
- Karpathy coding principles (think before coding, surgical changes)
- Commit, branch, and PR conventions
- Per-project memory via Obsidian (PROJECT, MISTAKES, CONTRACT files)
- Token optimization via RTK and Headroom
- Safety hooks (block dangerous commands, scan secrets)
- Persistent memory across sessions via claude-mem
Screenshots
Obsidian graph view (PROJECT, MISTAKES, CONTRACT linked)
RTK token savings
Video Walkthrough
Coming soon. Full setup walkthrough covering: clone, setup.sh, filling in CLAUDE.md…
Top comments (0)