infinite-brain-os: Command for Claude Code

.claude/commands/onboard-business.md

onboard-business is a command for Claude Code from starmynd-org/infinite-brain-os. It costs 44 tokens per session (678 once invoked), scanned A, original, MIT.

A command that interviews someone about their business and recommends what to build in their AI work system. It can also compare an updated business with an existing setup.

In plain words
What is it for?
Use it for a first business onboarding or a later review. It creates a business map and recommends a limited set of departments, knowledge areas, and workflows based on the interview.
Why use it?
It helps replace guesswork with a bounded starting plan, including what to build later and what not to build yet.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is starmynd-org/infinite-brain-os's own configuration. It tells Claude Code how to work on infinite-brain-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything infinite-brain-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to starmynd-org/infinite-brain-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/starmynd-org/infinite-brain-os/main/.claude/commands/onboard-business.md
Clone the repo
git clone --depth 1 https://github.com/starmynd-org/infinite-brain-os

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for onboard-business

README.md
[![agentmods](https://agentmods.dev/badge/commands/starmynd-org/infinite-brain-os/onboard-business/github.svg)](https://agentmods.dev/commands/starmynd-org/infinite-brain-os/onboard-business)
Your own site
<a href="https://agentmods.dev/commands/starmynd-org/infinite-brain-os/onboard-business"><img src="https://agentmods.dev/badge/commands/starmynd-org/infinite-brain-os/onboard-business/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for onboard-business

Your own site · 80×15
<a href="https://agentmods.dev/commands/starmynd-org/infinite-brain-os/onboard-business"><img src="https://agentmods.dev/badge/commands/starmynd-org/infinite-brain-os/onboard-business.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00678
Opus 5 $0.00022 $0.00339
Sonnet 5 $0.00009 $0.00136
Haiku 4.5 $0.00004 $0.00068

Measured 12d ago against content hash a1622c98e82e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

onboard-business scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/onboard-business.md · 66 lines

What it actually says

/onboard-business

Sit down with the brain and let it learn your business, then have it tell you what to build. One command runs the whole front door:

/onboard-business

Optionally with context:

/onboard-business We run a small candle studio, mostly wholesale plus a web shop. I want
help figuring out where to start.

This command should:

  1. check for an existing business map under intake/processed/ and an existing architecture inventory, and choose the mode:
    • first run: no map exists; run the full interview
    • re-run: a map exists; confirm what still holds, interview only the delta, and diff recommendations against the architecture that already exists
  2. run the interview per [[skill-interview-business]]: plain language, one question at a time, phase playbacks, business map written to intake/processed/<date>-business-map.md
  3. produce the bounded recommendation set per [[skill-recommend-architecture]]: at most one department, three namespaces, three workflows, with a parked Later list and a non-empty do-not-build-yet list, every item quoting the person's own words; when the interview surfaced a real signal, the set may close with an optional tooling note (Obsidian, n8n, Paperclip) pointing to docs/local-tooling-setup.md, outside the ceiling and never pushed
  4. present the set and let the person accept a subset; nothing is scoped without an explicit acceptance
  5. hand the accepted subset to [[workflow-onboard-business-architecture]], which creates one project per accepted item and generates a launchable swarm sprint folder for each, then tells the person exactly how to launch each sprint in a new terminal
  6. leave the run record in outputs/

The command is thin on purpose: the interview method lives in the skill, the judgment lives in the skill, the scoping lives in the workflow. This file only wires them.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 66 lines · 44 tokens per session scan A a1622c98e82e

Subscribe to this mod's changes

onboard-business is a command published in the GitHub repository starmynd-org/infinite-brain-os (248 stars, last pushed 16d ago), licensed MIT. It adds 44 tokens to every session and 678 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.