setup

setup is a command for Claude Code from signalcompose/claude-tools. It costs 18 tokens per session (1,808 once invoked), scanned D, original, MIT.

An interactive setup wizard for chezmoi, a tool that manages configuration files such as shell settings, with optional age encryption and 1Password integration.

In plain words
What is it for?
Use it to check required tools, initialize or clone a chezmoi setup, configure encryption or 1Password integration, and verify the result.
Why use it?
It guides first-time setup and distinguishes between creating a new configuration and copying an existing one, reducing setup mistakes on a new computer.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/USERNAME/.config/chezmoi/key.txt.

Part of the chezmoi plugin — 6 commands shipped together

Good fit Use it to check required tools, initialize or clone a chezmoi setup, configure encryption or 1Password integration, and verify the result.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add signalcompose/claude-tools
Claude Code
/plugin install chezmoi

Made for: Claude Code.

Or install chezmoi, the plugin that ships this one along with the rest of its 6 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/signalcompose/claude-tools/setup/github.svg)](https://agentmods.dev/commands/signalcompose/claude-tools/setup)
Your own site
<a href="https://agentmods.dev/commands/signalcompose/claude-tools/setup"><img src="https://agentmods.dev/badge/commands/signalcompose/claude-tools/setup/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 setup

Your own site · 80×15
<a href="https://agentmods.dev/commands/signalcompose/claude-tools/setup"><img src="https://agentmods.dev/badge/commands/signalcompose/claude-tools/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,808 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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 $0.00018 $0.01808
Opus 5.5 $0.00007 $0.00723
Sonnet 5.5 $0.00004 $0.00362
Haiku 4.5 $0.00002 $0.00181

Measured 1mo ago against content hash 688b3ead6ff5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

setup scanned grade D with 2 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 1mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 ~/.config/chezmoi/key.txt

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

chezmoi add --encrypt ~/.ssh/id_rsa
plugins/chezmoi/commands/setup.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chezmoi Setup Wizard

Overview

Interactive setup guide for chezmoi dotfiles management with age encryption and 1Password integration.

Capabilities:

  • Guides through 5-phase setup
  • Supports age encryption and 1Password integration
  • Handles both new setup and clone existing scenarios

Use when: "set up chezmoi", "configure dotfiles", "initialize chezmoi", "first time setup", "new machine setup", "chezmoi初期設定", "dotfiles設定", "1Password連携", "初回セットアップ"

Don't use for: Updating existing dotfiles, syncing changes, checking status

5 Phases:

  1. Environment check (tools availability)
  2. Detect existing setup
  3. Setup mode selection (new vs clone)
  4. Guided setup (new machine or clone existing)
  5. Verification

Execution

Follow the 5 phases sequentially. Read the Reference sections for detailed instructions.

Phase 1: Environment Check

Check if required tools are installed (see Reference: Phase 1 below).

Phase 2: Detect Existing Setup

Check if chezmoi is already configured (see Reference: Phase 2 below).

Phase 3: Mode Selection

Based on existing setup, ask user which mode to proceed with (see Reference: Phase 3 below).

Phase 4: Setup Guide

Based on selection:

  • New setup (first machine): See Reference: Phase 4A below
  • Clone existing (second+ machine): See Reference: Phase 4B below

Phase 5: Verification

After setup, verify everything works (see Reference: Phase 5 below).

Reference: Phase 1 - Environment Check

Check if required tools are installed:

echo "🔍 Checking required tools..."
echo ""

# Check chezmoi
if command -v chezmoi &> /dev/null; then
  echo "✅ chezmoi: $(chezmoi --version)"
else
  echo "❌ chezmoi: Not installed"
  echo "   Install with: brew install chezmoi"
fi

# Check age
if command -v age &> /dev/null; then
  echo "✅ age: $(age --version 2>&1 | head -1)"
else
  echo "❌ age: Not installed"
  echo "   Install with: brew install age"
fi

# Check 1Password CLI
if command -v op &> /dev/null; then
  echo "✅ op: $(op --version)"
else
  echo "⚠️ op: Not installed (optional)"
  echo "   Install with: brew install --cask 1password-cli"
fi

# Check GitHub CLI
if command -v gh &> /dev/null; then
  echo "✅ gh: $(gh --version | head -1)"
else
  echo "⚠️ gh: Not installed (optional)"
  echo "   Install with: brew install gh"
fi

echo ""

Read the full file on GitHub · 289 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. 1mo ago First seen · 289 lines · 18 tokens per session scan D 688b3ead6ff5

Subscribe to this mod's changes

setup is a command published in the GitHub repository signalcompose/claude-tools (4 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,808 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.