kochetkov-ma/claude-brewcode▌

Reduces token count in prompts and docs by 20–40% using 41 research-backed optimization rules. \n \n Applies rules across six categories: Claude behavior, token efficiency, structure, reference integrity, perception, and LLM comprehension \n Three optimization modes: light (text cleanup only), medium (balanced restructuring, default), and deep (aggressive compression and rephrasing) \n Processes single files or entire directories of markdown files, with built-in quality checks for reference vali

Streamline Claude Code memory files through 4 interactive optimization steps. \n \n Removes duplicate entries already present in CLAUDE.md or rules files, then migrates remaining entries to appropriate persistent config locations \n Compresses remaining memory entries using LLM-efficient formatting (prose to tables, verbose descriptions to imperatives) \n Validates final state by checking for broken references, contradictions, and orphaned files \n Typical reduction of 30–50% token count in memo