setup-wizard

setup-wizard is a skill for Claude Code from mishahanin/heading-os. It costs 92 tokens per session (1,969 once invoked), scanned A, original, Apache-2.0.

An interactive setup wizard for personalizing HEADING OS and 31C workspaces. It asks questions, turns short answers into fuller documents, stores API keys securely, and reports setup progress.

In plain words
What is it for?
Use it when creating or completing a workspace setup, answering configuration questions, adding credentials, and checking completion status.
Why use it?
It replaces a scattered initial setup with a guided process that records the information the workspace needs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/apply-wizard-answers.py --question <id> --value-from-stdin.

Good fit Use it when creating or completing a workspace setup, answering configuration questions…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mishahanin/heading-os
agentmods
npx agentmods add skills/mishahanin/heading-os/setup-wizard

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 setup-wizard

README.md
[![agentmods](https://agentmods.dev/badge/skills/mishahanin/heading-os/setup-wizard.svg)](https://agentmods.dev/skills/mishahanin/heading-os/setup-wizard)
Your own site
<a href="https://agentmods.dev/skills/mishahanin/heading-os/setup-wizard"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/setup-wizard.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,969 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 $0.00092 $0.01969
Opus 5 $0.00046 $0.00984
Sonnet 5 $0.00018 $0.00394
Haiku 4.5 $0.00009 $0.00197

Measured 3d ago against content hash 22228833cd13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

setup-wizard 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 3d 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/skills/setup-wizard/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup Wizard

This skill runs an interactive, per-question setup flow that personalizes a fresh workspace. See docs/superpowers/specs/2026-04-24-setup-wizard-design.md (data overlay: .heading-os-data/docs/superpowers/specs/2026-04-24-setup-wizard-design.md) for the full contract.

Preconditions

Before starting, Claude MUST:

  1. Run python scripts/apply-wizard-answers.py --status to detect the audience and current completion state.
  2. If exit code is 4 (ceo-master detected), print the abort message from stderr AND stop immediately. Do not proceed. Do not offer --force-ceo-master to the end user; it is a test-only override.
  3. If exit code is 1, surface the schema error and stop.

Source of Truth

All question data (prompt, example, help, type, id) is returned by --status in each rows entry. Use those fields directly. Do NOT cat, Read, or otherwise open wizard-questions.yaml yourself. The YAML lives in different paths depending on workspace layout: config/ on CEO master, corporate/config/ on exec. The apply script already resolves the correct path via its internal resolver. Reading the YAML directly will fail on exec workspaces.

First-Run Flow (empty answers.json)

Announce:

Welcome. I'll ask you ~N questions to set up your workspace. After each one I'll show you an example answer so you know what I'm looking for.

Rules:

  • Type an answer and press Enter.
  • Type skip if you don't want to answer - you can come back later.
  • Type example if you want me to read the example again.
  • Type help if you want me to explain what the question is for.
  • Nothing is saved until you confirm each answer.

Ready? Let's start.

Then walk through each question from the --status rows where status is pending, in bank order.

Per-Question Flow

Render each question:

Q<N> of <TOTAL> - <label>
---------------------------
<prompt>

  Example: <example>

Your answer: _

Wait for user input. Branch by type.

Read the full file on GitHub · 203 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. 3d ago First seen · 203 lines · 92 tokens per session scan A 22228833cd13

Subscribe to this mod's changes

setup-wizard is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 92 tokens to every session and 1,969 once invoked, about $0.0005 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 2026-09-03.