brain-setup
Skill1 starsChanged 39 days agoApache-2.0View on GitHub
Scaffolds the Brain folder system for a new operator from scratch — prompts for your name, company, Brain root path, and departments (or use defaults), creates the full Master Brain + dept Brains hierarchy with starter CLAUDE.md files and a three-surface-rule primer, seeds DASHBOARD.md + awareness.md, and walks you through connecting the sessionstart + sessionend skills. Use when: "set up my brain", "build my brain structure", "initialize my brain", "brain setup", "create my department brains", "install the brain", "set up the brain system", "build out my brain folders", "I want to start using the Brain".
5 other projects use a version of this.
Adopted by
Most recently taken up by
- mindmuxai/brain.mdtheir own version, first seen Oct 25, 2026
- RumbleJack56/skillstheir own version, first seen Oct 20, 2026
- VGBRO/claude-skillstheir own version, first seen Oct 11, 2026
- katharinaecke/second-brain-starter-kittheir own version, first seen Aug 14, 2026
- zenianielsen/founder-ostheir own version, first seen Jul 3, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- mindmuxai/brain.md★ 594same name
- katharinaecke/second-brain-starter-kit★ 3same name
- RumbleJack56/skills★ 2same name
- zenianielsen/founder-os★ 2same name
- VGBRO/claude-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- advisor-modeSkill
- ceo-briefSkill
- cerebro-doctorSkill
- council-modeSkill
- daily-briefSkill
- decisionSkill
- memory-attribution-lintSkill
- memory-recallSkill
- orchestrator-modeSkill
- sessionendSkill
- sessionstartSkill
- skill-manageSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 53
If the operator has no custom departments in mind, offer these as a starting point.
- Distinctive: line 64
Always ask before applying.
- Distinctive: line 73
All paths are collected from the operator at runtime in Stage 1.
- Distinctive: line 76
After Stage 1, the pattern is:
- Distinctive: line 119
Never overwrite existing content: Before creating any folder or file, check if it exists.
- Distinctive: line 126
Scaffold the docs, don't leave them empty: Every folder the skill creates gets a starter doc (CLAUDE.md, README.md, DASHBOARD.md, …
- Distinctive: line 134
Verify before signing off: After scaffolding, list every folder + file that was created and confirm each exists.
- Distinctive: line 139
Do not embed any operator-specific identifiers into the scaffolded files.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brain Setup
Guided first-time setup that builds the Brain folder system from scratch. Prompts for operator info and departments, scaffolds the full structure on disk, seeds a working DASHBOARD.md + awareness.md + workspace CLAUDE.md + per-dept CLAUDE.md files, and hands off with clear instructions for connecting the session rituals (sessionstart + sessionend).
Time to complete: ~7 minutes.
⚠️ FIRST-TIME SKILL — No Brain Check
This skill creates the Brain. There is nothing to check yet. Skip any Brain Check. Begin directly with Stage 1.
STAGE ROUTING
| Where the operator is | Stage | Reference file |
| Just started — no info collected yet | Stage 1: Intake | references/stage1_intake.md |
| Profile confirmed, ready to build folders + docs | Stage 2: Scaffold | references/stage2_scaffold.md |
| Folders built, ready to verify + connect session rituals | Stage 3: Connect | references/stage3_connect.md |
| Running full setup end-to-end | All stages in sequence | Read all three reference files |
DEFAULT DEPARTMENTS (example pattern)
If the operator has no custom departments in mind, offer these as a starting point. Folder names are lowercase kebab-case; display names are friendly for docs.
| Code | Folder (kebab-case) | Display name | Purpose |
| ops | ops/ | Operations | Company infrastructure, SOPs, skills, dashboards |
| sales | sales/ | Sales | Pipeline, outreach, proposal tracking |
| delivery | delivery/ | Delivery | Client work, projects, service execution |
| products | products/ | Products | Product builds, packaging, pricing |
| content | content/ | Content | Marketing, social, content ops |
Always ask before applying. Accept any list the operator provides.
Custom departments are welcome — accept any list, auto-convert names to kebab-case, confirm with operator before building.
WORKSPACE PATHS
All paths are collected from the operator at runtime in Stage 1. Nothing is hardcoded — this skill works for any operator on any machine.
After Stage 1, the pattern is:
{workspace_root}/ ← top-level project folder
{workspace_root}/CLAUDE.md ← workspace-root front door (created in Stage 2)
{workspace_root}/mission-control/ ← Master Brain (Chief of Staff)
{workspace_root}/mission-control/DASHBOARD.md
{workspace_root}/mission-control/awareness.md
{workspace_root}/mission-control/sessions/
{workspace_root}/mission-control/decisions/
{workspace_root}/mission-control/skills/ ← skill source-of-truth layer
{workspace_root}/mission-control/state/ ← live state
{workspace_root}/{dept-folder}/ ← one per department
{workspace_root}/{dept-folder}/CLAUDE.md ← dept-scoped front door
{workspace_root}/{dept-folder}/brain/
{workspace_root}/{dept-folder}/brain/README.md
{workspace_root}/{dept-folder}/brain/sessions/
{workspace_root}/{dept-folder}/brain/decisions/
{workspace_root}/{dept-folder}/brain/decisions/decisions.md
{workspace_root}/{dept-folder}/brain/pipeline/SURFACE PRIMER (seeded into workspace CLAUDE.md)
The workspace CLAUDE.md seeds this primer so every new session knows where tasks belong:
- Claude Code = on-metal executor. Runs in the operator's terminal with Mac/Linux FS, local models, and git. Surface for drafting, planning, synthesis, file ops, repo work, local model runs, anything that touches process-state on the machine.
- Operator = relationship + decision layer. Human judgment, vendor/customer touches, sign-offs.
Routing rule: Everything goes through Claude Code unless the Operator needs to step in for a relationship or hard decision.
KEY RULES
- Confirm before building. Present the full profile and folder plan to the operator and wait for a 'yes' before running any commands. A wrong root path is painful to undo.
- Never overwrite existing content. Before creating any folder or file, check if it exists. If a Brain is partially built, surface what's there and ask how to proceed — never silently skip or clobber existing files.
- Folders use lowercase kebab-case.
ops/, notOps/.content-creation/, notContentCreation/. Custom dept names get auto-converted. - Scaffold the docs, don't leave them empty. Every folder the skill creates gets a starter doc (CLAUDE.md, README.md, DASHBOARD.md, awareness.md, decisions.md). A Brain with empty folders is indistinguishable from a broken Brain.
- Stop at instructions for session rituals — do not edit them. Give the
operator the Brain root path + explicit what-to-change-where for
sessionendANDsessionstart. Don't reach into another skill's files. - Verify before signing off. After scaffolding, list every folder + file that was created and confirm each exists. A setup that silently fails is worse than one that errors loudly.
- Never seed operator-specific data. This skill ships to external operators. Do not embed any operator-specific identifiers into the scaffolded files. The operator supplies their own profile via Stage 1 intake — the skill scaffolds the structure, the operator owns the content.
Scope Contract
| Dimension | Scope |
| Read paths | Operator input collected via Stage 1 prompts (name, company, workspace root, department roster) |
| Write paths | New {workspace_root}/, {workspace_root}/mission-control/**, {workspace_root}/{dept}/brain/**, and starter docs — written once during Stage 2 scaffold |
| MCP / tool surface | Python stdlib (os, pathlib) for folder creation; file I/O for starter docs |
| Network egress | None |
| Surface | Claude Code |
| Credentials | None |
| Escalation trigger | If target root has existing content → HALT and surface per Rule 2; require operator confirmation or new path before any write |
<!-- AUTOLINK-START — Obsidian wikilink graph backfill (idempotent; safe to re-run) -->References (auto-wikilinks)
- [[DASHBOARD]]
- [[awareness]]
- [[decisions]]
- [[stage1_intake]]
- [[stage2_scaffold]]
- [[stage3_connect]]
<!-- AUTOLINK-END -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

