setup

A guided setup wizard for Founder OS, a file-based system for organising a founder’s identity, priorities, decisions, routines, knowledge, and roles. It creates the files needed for the system to work.

In plain words
What is it for?
Use it to install or restart Founder OS and complete its onboarding interview.
Why use it?
It gives new users a structured starting point instead of making them decide which files to create and what information to enter.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/arcassystems/founderos/setup
Clone the repo
git clone --depth 1 https://github.com/ARCASSystems/FounderOS

Made for: Claude Code.

Per session 120 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,340 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00120 $0.01340
Opus 5 $0.00060 $0.00670
Sonnet 5 $0.00024 $0.00268
Haiku 4.5 $0.00012 $0.00134

Measured 2d ago against content hash c1c822bc188c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. `skills/founder-os-setup/SKILL.md` relative to the working directory. This is the git clone, curl, and ZIP case.
.claude/commands/setup.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Founder OS setup

Entry point for the Founder OS setup wizard. Triggers the founder-os-setup skill, which runs a guided interview and generates every file the OS needs to operate: identity, priorities, decisions, cadence, brain, roles.

Argument: $ARGUMENTS - optional. Pass --reset (or reset) to force a re-run on an existing install.

Procedure (in order)

  1. Read the install's state, in this order of authority. Setup writes state/setup-progress.json after every phase and state/setup-complete.json only after the final health check, so these markers - not the identity file, which lands five phases early - are what say whether setup finished.

    A marker counts only if it reads as the record it claims to be: valid JSON, non-empty, carrying its fields. An empty or truncated file is a marker that failed to write, which means setup did NOT reach that point - treat it as absent rather than as proof. A zero-byte completion marker suppressing setup entirely is the worst reading of the same file.

    • state/setup-progress.json exists: setup was interrupted. This is read first and wins even when a completion marker sits beside it, because finishing setup deletes the progress marker - the two coexisting means a setup started and did not finish, and resuming that is recoverable where opening silently is not. Skip the re-run question entirely - do not make the founder diagnose anything. Tell them in one sentence where it stopped, then go to step 3 and resume from the marker's next_phase (the skill's Resuming rule): Setup did not finish last time - it stopped after <finished_phase in plain words>. Picking up right where we left off.
    • state/setup-complete.json exists, OR neither marker exists but core/identity.md does (an install set up before the markers existed): set up already. Go to step 2.
    • Neither marker nor core/identity.md: fresh install. Go to step 3.
  2. If set up already AND $ARGUMENTS does NOT contain reset:

    Ask the founder, as a single message, nothing else:

Read the full file on GitHub · 61 lines

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. 2d ago First seen · 61 lines · 120 tokens per session scan A c1c822bc188c

Subscribe to this mod's changes

setup is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 18d ago), licensed MIT. It adds 120 tokens to every session and 1,340 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.