{"slug":"mdbrain","title":"mdbrain","description":"A native Claude Code extension that prevents AI from over-refactoring your intentional code. Combines XML-structured protocols (BRAIN/CRAFT/PERF) with a 16-entry false-positive catalog, enforced by a five-layer Safety Net: permissions deny list, PreToolUse hook, tool-scoped subagents, path-scoped rules, and behavioral protocols. Coexists non-destructively with existing CLAUDE.md and memory/.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-11T06:00:01.664Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/chanjoongx/mdbrain.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"mdbrain","source":{"sha":"434e7b337aff22e31964981053c89205e2330088","url":"https://github.com/chanjoongx/mdbrain.git","source":"url"},"homepage":"https://github.com/chanjoongx/mdbrain","description":"A native Claude Code extension that prevents AI from over-refactoring your intentional code. Combines XML-structured protocols (BRAIN/CRAFT/PERF) with a 16-entry false-positive catalog, enforced by a five-layer Safety Net: permissions deny list, PreToolUse hook, tool-scoped subagents, path-scoped rules, and behavioral protocols. Coexists non-destructively with existing CLAUDE.md and memory/."}]}}