agentmods.dev

setup: Instructions file for Claude Code

CLAUDE.md

setup CLAUDE.md is an instructions file for Claude Code from cknadler/setup. It costs 1,067 tokens per session, scanned A, original, MIT.

A set of instructions and scripts for setting up a fresh macOS development computer.

In plain words
What is it for?
It is for installing Homebrew packages and selected applications, applying system defaults, choosing computer profiles, running tests and linting, and checking setup health.
Why use it?
It organizes software installation, macOS settings, progress tracking, diagnostics, and tests so the setup can be repeated and checked.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is cknadler/setup's own configuration. It tells Claude Code how to work on setup 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 setup configures →

not rated 10repo 5mo ago A scan 1,067 tokens original MIT
View source ↗ cknadler/setup
Reuse

Borrowing it

Nothing to install: this file belongs to cknadler/setup. 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/cknadler/setup/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/cknadler/setup

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 CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cknadler/setup/claude-md"><img src="https://agentmods.dev/badge/instructions/cknadler/setup/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,067 This file is loaded in full into every session.
When invoked 1,067 The same file — it is already loaded in full.
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 $0.01067 $0.01067
Opus 5.5 $0.00427 $0.00427
Sonnet 5.5 $0.00213 $0.00213
Haiku 4.5 $0.00107 $0.00107

Measured 2mo ago against content hash 1af7dbf5d4b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

setup CLAUDE.md 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 2mo 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.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

setup

Bootstrap a fresh macOS dev environment.

Layout

  • bootstrap — entrypoint: argument parsing, logging, step orchestration.
  • lib.sh — step functions (step_xcode, step_homebrew, …), logging (log_info, log_warn, …), state tracking (state_*), and read-only doctor probes (doctor_*). Sourced by bootstrap.
  • Brewfile — default packages installed on every machine, including the everyday apps (Signal, Spotify, Dropbox, Obsidian, …) and mas HEIC.
  • Brewfile.home — home-machine extras (Discord, VLC, Synology Drive, …); auto-installed when "personal" is chosen.
  • Brewfile.media — media apps (Plex, YACReader).
  • Brewfile.music — audio production. Out of scope for current work.
  • .osx — defaults write customizations; run last (some changes require a restart).
  • Makefile — make test, make lint, make doctor, make all.
  • tests/ — bats-core test suite (63 tests) using PATH-shim mocks under tests/fixtures/bin/. Tests source lib.sh directly and exercise step functions with isolated $HOME and stubbed subprocess calls.
  • colors/ — terminal color theme assets.

Usage

./bootstrap                Interactive: ask machine type, then optional extras.
./bootstrap --all          Non-interactive: run every core step (in scope).
./bootstrap --only S1,S2   Run only named steps.
./bootstrap --doctor       Read-only state report. Installs nothing.
./bootstrap --force        Re-run completed steps.
./bootstrap --help         Usage.

State and logs live in ~/.local/state/setup/:

  • completed — newline-delimited list of finished steps; re-runs skip these.
  • bootstrap-<timestamp>.log — every run's output, tee'd from stderr.

Steps

Core steps (--all order, and run on every machine in the interactive flow): xcode, homebrew, brewfile, claude, chezmoi, marta, vim_anywhere, bindings, osx.

Extra steps: brewfile_home, brewfile_music, brewfile_media, crawl. The interactive flow asks "work or personal?" — both run the core steps; a personal machine additionally runs brewfile_home and is prompted (y/n) for brewfile_music, crawl (games), and brewfile_media. Extras are also reachable directly via --only.

Read the full file on GitHub · 97 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. 2mo ago First seen · 97 lines · 1,067 tokens per session scan A 1af7dbf5d4b1

Subscribe to this mod's changes

setup CLAUDE.md is an instructions file published in the GitHub repository cknadler/setup (10 stars, last pushed 5mo ago), licensed MIT. It adds 1,067 tokens to every session, about $0.0043 per session on Opus 5.5. 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 2026-08-31.

Related

setup CLAUDE.md compared with instructions from other repositories

setup CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
setup CLAUDE.mdcknadler/setupInstructions file105mo agoMITA1,067Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot