{"id":"2078784709253841039","url":"https://x.com/Bober_smart/status/2078784709253841039","text":"","author":{"name":"Bober_smart","username":"Bober_smart","avatarUrl":"https://pbs.twimg.com/profile_images/2050347090543300608/p1PlS_hc_200x200.jpg"},"createdAt":"Sun Jul 19 10:11:11 +0000 2026","engagement":{"replies":23,"retweets":16,"likes":155,"views":1979238},"article":{"title":"Claude Second Brain & Folder Workflow: The Complete Guide","previewText":"Build your AI-native second brain using simple Markdown folders and a CLAUDE.md index file map\n\"Second brain\" sounds a bit pretentious, but at the end of the day, it is just a handful of text files","coverImageUrl":"https://pbs.twimg.com/media/HNlPS-NXgAA-bPL.jpg","content":"## Build your AI-native second brain using simple Markdown folders and a [CLAUDE.md](https://claude.md/) index file map\n\n\"Second brain\" sounds a bit pretentious, but at the end of the day, it is just a handful of text files stashed in a few folders, managed by a single index file that guides the AI on where to look. No Obsidian, no complex databases, no bloated apps, just plain Markdown sitting on your drive. \n\nIn this walkthrough, we will build this architecture from the ground up: organizing the directory structure, writing your roadmap (the [CLAUDE.md](https://claude.md/) file), setting naming conventions, and explaining exactly how the agent parses it all. By the time you are done, you will have a robust system you can replicate and start populating immediately.\n\nThe Short Answer\n\nA \"second brain\" is nothing more than a collection of flat .md files organized in simple folders, with a single [CLAUDE.md](https://claude.md/) file in the root serving as your index. It acts as a compass, informing the agent where information resides, how files are structured, and the protocols for reading them. The golden rule: one topic per file. The [CLAUDE.md](https://claude.md/) is the map the agent follows to navigate your knowledge. You do not need a dedicated note-taking app.\n\nWhat You will Need\n\nAn AI agent that can read project directories (like Claude Code or similar).  \n\nAny text editor. These are standard .md files; they work with everything.  \n\nFive minutes. That is enough time to set up the folders. You can fill them in as you go, there is no need to front-load all your data. \n\nNote: There are no installation scripts or complex configurations involved. This is a file structure and an index, not a software product.\n\nThe Principle: Flat Files Over Apps \n\nThe instinct to download Obsidian or build a fancy Notion database is usually a trap. Apps impose their own proprietary formats, storage logic, and interfaces, which often create friction for an AI. An agent works best when it can read a simple text file on your disk directly, without any middle layers.\n\n That is why the foundation here is flat Markdown files. \"Flat\" means plain text with standard formatting (headers, bullet points), no nested databases and no proprietary links. It is accessible anywhere, readable by both humans and AI. This is not a sacrifice for the sake of simplicity, it is a strategic advantage: the cleaner the format, the fewer walls stand between your knowledge and the agent.\n\nThe Skeleton: Semantic Folders \n\nThe layout relies on semantic organization, grouping folders based on their content. Here is the basic structure:\n\n![](https://pbs.twimg.com/media/HNlRc3hXcAAHbGG.jpg)\n\nThese three core folders cover almost every use case:  \n\nnotes/: Facts and topic-specific entries. If you learn something, distill it here. One file per topic.  \n\npeople/: Cards for contacts or companies: who they are, meeting summaries, key details. One file per person.  \n\nprojects/: Project status: what you are currently working on, where you paused, and the next steps. \n\nAdditionally, use the root-level files for metadata about your workflow: [MEMORY.md](https://memory.md/) (long-term, core info), [LEARNINGS.md](https://learnings.md/) (lessons learned), and [decisions.md](https://decisions.md/) (an audit log of your choices).\n\n[CLAUDE.md](https://claude.md/), The Map \n\nThis is the brain's nervous system. Folders are just storage; to make them actionable, you need a map. The [CLAUDE.md](https://claude.md/) file in the root tells the agent how to interpret your structure. \n\nWhy [CLAUDE.md](https://claude.md/)? If you use Claude Code, it loads this file into the system prompt automatically on startup. You do not have to prompt the agent to \"read the map\", it already knows the rules of engagement before your first question. \n\nExample of your map file:\n\n![](https://pbs.twimg.com/media/HNlSCWFXMAAy7Ea.jpg)\n\nPro-Tip: Leveraging @-Connections \n\nFor a more advanced setup, you can prime the agent: your [CLAUDE.md](https://claude.md/) can directly reference core files using @ paths. By adding [@MEMORY](https://t.me/MEMORY).md or [@decisions](https://t.me/decisions).md to the map, the agent keeps that high-level context in its active memory at all times. Use this sparingly, only for what truly needs to be in focus consistently.\n\nNaming Rules: Discipline is Everything\n\nThe \"one file = one topic\" rule is where most systems succeed or fail.\n\nOne File = One Topic. Avoid \"dumping\" several unrelated points into [notes.md](https://notes.md/). If it is about \"Tax Policy,\" create [tax-policy.md](https://tax-policy.md/).\n\nTopic as Name. Name the file for what it contains. Use [ivan-petrov.md](https://ivan-petrov.md/) instead of [note-12.md](https://note-12.md/).  \n\nUnified Style. Stick to lowercase and hyphens to avoid ambiguity. \n\n## How the Agent Reads It\n\nWhen you initiate a session, the agent ingests [CLAUDE.md](https://claude.md/). When you ask a question, it uses the map to locate the correct file, parses it, and synthesizes an answer, complete with a citation. If the info is not there, it reports a failure rather than hallucinating. Your only responsibility is maintaining a clean structure; the agent handles the retrieval.\n\nCommon Pitfalls\n\n![](https://pbs.twimg.com/media/HNlS7uWW0AAaIfd.jpg)\n\n## FAQ\n\nMust the map be called [CLAUDE.md](https://claude.md/)? If you use Claude Code, yes, it is automatic. For other agents, use a [README.md](https://readme.md/) or an equivalent root-level index.  \n\nHow many folders should I start with? Keep it simple. Stick to three primary folders and your root-level files. Expand only when a topic becomes large enough to warrant its own directory.  \n\nDo I have to move all my old notes? No. Build the skeleton now and migrate or create new content as you go. \n\nThe Bottom Line \n\nYour second brain is simply a mix of flat .md files, a strict \"one topic = one file\" discipline, and a [CLAUDE.md](https://claude.md/) map to guide the agent. Forget the complex software, just keep your text files organized on your disk. Invest your time in the map; a clear [CLAUDE.md](https://claude.md/) is the difference between a disorganized mess and a functional AI assistant."},"adhxContext":{"savedByCount":1,"publicTags":[],"previewUrl":"https://adhx.com/Bober_smart/status/2078784709253841039"}}