AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Brain Setup

skill-cerebrocybersolutions-libro-brain-setup · by cerebrocybersolutions

>

No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-cerebrocybersolutions-libro-brain-setup

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access Used
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-cerebrocybersolutions-libro-brain-setup)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Brain Setup? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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

  1. 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.

  1. 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.

  1. Folders use lowercase kebab-case. ops/, not Ops/. content-creation/,

not ContentCreation/. Custom dept names get auto-converted.

  1. 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.

  1. Stop at instructions for session rituals — do not edit them. Give the

operator the Brain root path + explicit what-to-change-where for sessionend AND sessionstart. Don't reach into another skill's files.

  1. 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.

  1. 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 |

References (auto-wikilinks)

  • [[DASHBOARD]]
  • [[awareness]]
  • [[decisions]]
  • [[stage1_intake]]
  • [[stage2_scaffold]]
  • [[stage3_connect]]

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.