Source: raw/5_Skills_to_Build_an_AI_Operating_System_Like_The_1%_Full_Guide.md — YouTube tutorial zElKhlFkqU4. Creator self-identifies as Ben running “an AI agency where we implement AI operating systems for businesses.” Sells “AI accelerator” community + 1-on-1 tech help + consulting. Skills shipped as a downloadable plugin ZIP (link in description). 2026-10-28 follow-ups from the same creator: raw/Build_a_Better_Claude_Second_Brain_than_99%.md (2026-09-07), raw/Stop_Using_Obsidian_for_Your_Second_Brain_Use_This_Instead.md (2026-08-29), raw/The_7_Levels_of_Using_Claude_Context_Explained_in_24_min.md (2026-04-11). See the “Added 2026-10-28” section.
A bundled five-skill kit that walks a single user (and eventually a team) from zero to a working Obsidian-backed second brain that Claude Code and Cowork can pull from. Each skill is a numbered stage; the kit is designed so you run them in order. Distinct from the Nate Herk AIS-OS 3-skill bundle (/onboard, /audit, /level-up) in that Ben’s bundle is opinionated about Obsidian + Relay-plugin permissions + Railway-hosted MCP — Nate’s is tool-agnostic about persistence layer.
Key Takeaways
Architecture overview
- Second brain = a folder on disk, visualized via Obsidian (a free overlay). The folder, not Obsidian, is the source of truth.
- Folder structure templates: solopreneur/professional vs business-with-team. The “business” structure includes
context/,daily/,projects/,intelligence/,resources/,skills/,departments/,teams/,onboarding/. The bundledOS setupskill picks one and scaffolds the directory tree +CLAUDE.mdfiles at each level. - CLAUDE.md as the routing map. Each subfolder gets its own
CLAUDE.mdthat tells Claude where to find which information — explicitly credited in the transcript to “Andre Karpathy … one of the leading AI researchers” (and is the Karpathy LLM-wiki pattern this vault implements; see _index).
The five skills
1. OS setup — initial scaffold
- Run
/os-setupafter picking a target folder. - Asks user vault type (solopreneur / professional / business).
- Generates folder structure + per-folder
CLAUDE.mdfiles. - Runs a 12-section context interview — biographical, company, market, team, infrastructure, ICP, etc. Each section has brain-dump + file-upload boxes. Recommendation in transcript: “order a six-pack and a pizza, sit down for hours, use Whisper Flow voice transcription, dump everything.” Output is structured by Claude into the populated folder.
- Final step: connect the folder as an Obsidian vault. Apply the PLN theme for visual polish (optional).
2. OS operator — daily real-time context refresh
- Run
/os-operatorto set up a scheduled task in Cowork that pulls real-time data from connectors (Fireflies meeting transcripts, Circle community threads, Slack DMs, Google Calendar, email — whatever the user has connected). - Each run produces a daily context brief in
daily/<date>.mdcontaining critical escalations, today’s calendar, team task lists, meeting transcripts, file updates. - Can DM your co-founder/team via Slack when something urgent appears.
- Limitation: scheduled tasks only run while the Cowork desktop app is open. To run autonomously with the laptop closed, route through Claude Routines + the OS MCP skill (#5).
3. OS optimizer — context bloat cleanup
- Run
/os-optimizerweekly or bi-weekly to audit the entire second brain. - Combines multiple named frameworks from the transcript:
- Anthropic’s architecture /
CLAUDE.md/ dream framework / managed-memory best practices - Caveman compression method
- Chroma context-route method
- Karpathy LLM-wiki (this vault’s pattern)
- Anthropic’s architecture /
- Sample output cited in the video: 1,700 files audited, 34 problems found, 32 fixed, health score 46 → 94.
- Fixes: dedup + merge, stale-context detection, broken wiki-links, format cleanup, irrelevant data removal, frontmatter + tags additions, folder reorganization proposals, conflicting-information resolution. Optimizes
CLAUDE.md+ index files for token efficiency. - Maps directly to the Lint operation in this vault’s
CLAUDE.md(vault schema) — seeCLAUDE.md§ Lint for the 17-check parallel implementation. - Anthropic’s announced dream feature (currently only in Managed Agents) is positioned as a future replacement, but for now this skill ships the open equivalent.
4. Team OS — multi-user sync + role permissions via Obsidian Relay
- Run
/team-osonce the single-user vault is working (transcript recommends ≥2 weeks of solo use first). - Installs the Obsidian Relay plugin (community plugin) for real-time multi-user folder sync. Set up by creating a Relay server, sharing the key with team members.
- Then swaps the upstream Relay plugin for “Bennai Relay” — Ben’s custom fork that adds role-based read/write permissions (member vs owner). Use case: strategy doc readable by everyone, editable only by founders.
- Comparison table from the transcript on shared-vault options:
| Approach | Real-time? | Permissions? | Token efficient? | Verdict |
|---|---|---|---|---|
| GitHub | No (manual push/pull) | Yes | Yes | Workable, not real-time |
| Google Drive / Notion via MCP | Yes | Yes | No — MCP adds latency, token cost, accuracy loss | Avoid at scale |
| Obsidian Sync (native) | No (click-to-sync) | No | Yes | Workable but no perms |
| Obsidian Relay + Bennai Relay | Yes | Yes (role-based) | Yes | Recommended |
5. OS MCP — Railway-hosted MCP server for autonomous routines
- Run
/os-mcpto expose the second brain as a remote MCP server so Claude Routines (cloud-hosted, run without laptop open) and Managed Agents can read/write to it. - Pipeline: installs Railway (referenced as
railwayinstall via Cowork or Code tab), guides through Railway account + API token, deploys the second brain as a server with a public vault-MCP URL. - User adds the MCP URL as a custom remote MCP in Cowork → Customize → Connectors → Add Custom.
- Then connects to the Relay account (email + password from #4) to authorize the server against the actual vault.
- End state: the same prompt that ran as a scheduled task can now run as a Routine in the Claude Code tab — selects “Remote” execution mode, picks a schedule, lists the connectors (Fireflies, Google Calendar, email, second-brain MCP). Runs even when the laptop is closed.
Mindset commentary (recurring in the transcript)
- Start simple, day-one is not perfection. Ben’s vault was 30-40 docs at start, hundreds at 6 weeks, thousands now.
- Context compounds. The agent your team has after 6 months is far more powerful than day-one — the value is in the accumulated context layer.
- Always select the second-brain folder in every new chat across providers (Cowork, Claude Code, Codex, etc.).
- If Claude doesn’t pull context automatically, instruct it explicitly to scan the vault before answering.
- Shared business AI fights “AI always agrees” syndrome — a referenced “institutional AI vs individual AI” article (link in resources) is the rationale for team-OS investment.
Added 2026-10-28 — what changed in Ben AI’s later videos
The creator is Ben AI (YouTube @BenAI92). Later videos show how this kit evolved; full current version in Ben AI’s Second Brain Playbook.
- Three of the five skills survive, renamed and free. “Build a Better Claude Second Brain than 99%” (Puzgmzv7t3Q, 2026-09-07) ships
/setup,/operatorand/optimizeras a free plugin ZIP./setupkeeps the 12-topic interview and adds, per topic, a box naming the software to pull from (the connector must already be connected). - Model advice. Ben says not to run
/setupon Fable 5.1 (“unnecessary token spend”; Opus 5 is enough) but to run/optimizeron Fable 5.1. His September optimizer run: 5,400 Markdown files across 822 folders, 56 issues found, 26 fixes applied. - The operator now targets routines too. It still creates a desktop scheduled task (9:00 a.m. daily in his demo) and saves its instructions as a prompt file in the brain; for laptop-closed runs you paste the same prompt into a Claude Code routine.
- Team OS and OS MCP are replaced by Baalda. From 2026-08-29 Ben recommends his open-source app Baalda (captions: “Balder”, “Balda”; repo naveedharri/baalda, Apache-2.0) instead of Obsidian Relay plus his fork. It bundles real-time team sync, per-file and per-member permissions, daily backups, version history and a built-in MCP endpoint, which removes the Railway deploy in step 5. He now calls the Relay-style workarounds “clunky”. Comparison: Where to Host a Claude Second Brain.
- “Bennai Relay” is “Ben AI Relay”. In the April video “The 7 Levels of Using Claude Context” (l5Diqeoffa4) Ben calls the fork “our Ben AI Relay plugin” and says Relay is free for up to three people and that Relay’s founder had permissions “in their pipeline”.
Open Questions
“Ben“‘s full name + channel— resolved 2026-10-28: channel is Ben AI (@BenAI92); the plugin is “Ben AI Relay”. Full surname still not stated in any transcript.- Bundled plugin ZIP URL — described as “first link in description”; not fetched as ai-research yet. Worth pulling once URL is known to confirm skill contents.
- PLN Obsidian theme — visualizer theme recommended in the video. Look up community-plugins listing.
- Caveman compression method + Chroma context-route method — referenced as named frameworks the optimizer skill uses. Sources not in the transcript. Caveman is plausibly the Caveman Claude Code plugin (concise-mode for token compression — see nine-claude-code-plugins-10x-faster); Chroma is plausibly Chroma’s open-source RAG context-routing paper. Verification recommended before citing.
- “Institutional AI vs individual AI” article — referenced as resource link, source not in transcript. Worth fetching.
Related
- nate-herk-claude-code-operating-systems-course — alternative AIOS framework (3Ms + 4Cs, AIS-OS repo). Tool-agnostic on persistence layer; this article opts for Obsidian + Relay specifically.
- nate-herk-every-level-of-claude — Nate Herk’s 5-level mastery framework
- claude-code-memory-architecture-comparison — companion video by same creator on memory storage/recall layer
- skill-systems-orchestrator-child-pattern — companion video by same creator on skill chaining
- claude-code-routines — cloud-hosted routines that step #5’s MCP enables
- scheduled-tasks — local scheduled tasks used in step #2
- cowork-getting-started — Cowork is the front-end where most of this is run
- connectors — Fireflies / Slack / Calendar / email connectors used by the operator
- 2026-claude-code-aios-pattern — cross-topic synthesis on the broader AIOS pattern
- Ben AI’s Second Brain Playbook — the October 2026 version of this kit (18 lessons)
- Where to Host a Claude Second Brain — Baalda vs Obsidian + Relay vs Drive vs Notion
- _index — the LLM-wiki pattern this vault implements + that the optimizer skill cites
- Ben AI’s Skill-Engineering Framework — his skill-building method.
Try It
- Pick a target folder. Anywhere on disk. Don’t worry about getting the structure perfect upfront.
- Download Obsidian (free) — Mac or Windows. Apply the PLN theme for visual polish (optional).
- If using the bundled plugin: download the ZIP from the video’s first description link, then in Cowork → Customize → Plugins → Create plugin → Upload plugin → drop the ZIP.
- Run
/os-setup. Pick solopreneur or business. Let the 12-section interview run end-to-end (block 2-3 hours; use Whisper Flow or similar voice-transcription for brain-dump speed). - Connect the resulting folder as an Obsidian vault. Open Obsidian → Open folder as vault → select.
- Set up daily refresh with
/os-operator. Choose your connectors (Fireflies, Slack, etc.). Approve the scheduled task. Leave Cowork open for now. - Run
/os-optimizerafter a week. Inspect the health-score report. Note what it merged/cleaned/flagged — this is the lint output for your second brain. - (Multi-user only) Add team sync with
/team-osafter at least 2 weeks of solo use. Configure roles (member / owner) for each shared folder. - (Autonomy upgrade) Set up
/os-mcpif you want the daily refresh to run with your laptop closed. Deploys via Railway → exposes vault as MCP → routine in Claude Code tab. - Alternative: if you already follow Nate Herk’s AIS-OS 3-skill bundle, compare framings — Nate’s onboard/audit/level-up vs Ben’s setup/operator/optimizer/team/MCP. Pick the persistence + permission setup that fits your team size.