About Claude Code - Brain Bootstrap

Most instruction systems hand you generic rules and hope the AI reads them. Brain Bootstrap works differently — it starts by mapping your project. Run /bootstrap once and a discovery engine scans your repo across 30+ languages: your actual build commands, your real test runner, the packages you already use, the files that must never be touched. From that, it auto-generates architecture docs, a domain glossary, and build conventions specific to this project — not a generic template. Claude Code goes into every session knowing your stack, your naming conventions, your rules. Then it keeps learning. Every correction becomes a permanent rule. Bash hooks block forbidden operations before they execute — deterministic scripts, not AI judgment. The knowledge base compounds with your codebase, session by session. The result: an assistant that knows your project the way a senior teammate does, and cannot unlearn it. The problem it solves: Claude Code is stateless by design — each session starts blank. So you end up re-explaining your stack, re-enforcing the same rules, re-correcting the same errors. Every. Single. Session. You become the AI's memory. What Brain Bootstrap gives you instead: Persistent memory — conventions, architecture, past mistakes embedded once and never forgotten Enforced rules — bash hooks that block violations before they run, no AI judgment involved Ready-to-use workflows — 31 slash commands (/plan, /review, /mr and 28 more), 49 skills, 5 specialist subagents Self-updating knowledge — the knowledge layer grows with your codebase, session by session Install once. Correct once. It never happens again.