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.
npx agentmods add instructions/ben196888/mac-set-up/claude-mdgit clone --depth 1 https://github.com/ben196888/mac-set-upWrote 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.
[](https://agentmods.dev/instructions/ben196888/mac-set-up/claude-md)<a href="https://agentmods.dev/instructions/ben196888/mac-set-up/claude-md"><img src="https://agentmods.dev/badge/instructions/ben196888/mac-set-up/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00768 | $0.00768 |
| Opus 5 | $0.00384 | $0.00384 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
mac-set-up 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 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Repo Does
This is a macOS development environment automation tool. Running ./install.sh sets up a complete dev environment in one shot: Homebrew, CLI tools, languages, IDEs, browsers, productivity apps, and system preferences.
Running
chmod +x install.sh
./install.sh
Individual scripts can also be run directly (e.g., ./languages/python.sh).
There are no build, lint, or test commands — this is a shell-based installer with no test suite.
Architecture
install.sh is the orchestrator — it sources or executes all other scripts in order:
essential.sh— Xcode CLT, Rosetta 2, Homebrew (with Apple Silicon vs Intel path detection viauname -m)cli_tools.sh— OpenSSL, ripgrep, ast-grep, tree, ackgit/install.sh— Git config, ed25519 SSH key generation, GitHub CLI authzsh/install.sh— Zsh, Oh My Zsh, Starship promptterminal.sh— Ghostty terminallanguages/— One script per language:javascript.sh(n + npm/yarn/pnpm/Deno),python.sh(pyenv + Poetry),rust.sh,go.sh,java.sh(SDKMAN),dotnet.sh,latex.shides.sh— VS Code, Cursorbrowsers.sh— Firefox (default), Chrome, Edge, DuckDuckGodevtools.sh— OrbStack, Docker CLI, kubectl, Helm, Postman, Google Cloud SDK, ChatGPT, Claude Code, Playwright CLI 9.5.agentic/install.sh— Agentic instructions, skills, and MCP setuptools.sh— AppCleaner, Spotify, Slack, Messenger, Signal, Discord, Rectanglemacos.sh— System defaults: Dock (auto-hide, left position), trackpad (tap-to-click, 3-finger drag, max speed), keyboard (Caps Lock→Control), input source shortcuts, Spotlight disabling
Key Conventions
- Homebrew prefix: Always use the
BREW_PREFIXvariable (set inessential.shbased on arch) rather than hardcoding paths./opt/homebrewon Apple Silicon,/usr/localon Intel. - Conditional tool init in
.zshrc: All tool initializations (pyenv, Poetry, SDKMAN, etc.) are wrapped incommand -v <tool> >/dev/null 2>&1guards so the shell doesn't break if a tool isn't installed. - Config files live alongside installers:
git/.gitconfigandgit/.gitignore_globalare copied bygit/install.sh;zsh/.zshrcis managed byzsh/install.sh. - Agentic setup source of truth: Manage reusable agent setup through
agentic/install.sh; configuration lives inagentic/agentic.conf. - Always use
cp, never symlinks: All install scripts must copy files/directories to their destination (e.g.cp,cp -r). Never useln -sorln -sf. This is a hard rule — do not change it.
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.
- 3d ago First seen · 44 lines · 768 tokens per session scan A 69f29acf781a
mac-set-up CLAUDE.md is an instructions file published in the GitHub repository ben196888/mac-set-up (11 stars, last pushed 24d ago), licensed MIT. It adds 768 tokens to every session, about $0.0038 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.
Other instructions, from other repositories
dotfiles AGENTS.md
AGENTS.md instructions for denysdovhan/dotfiles, covering agents repository guidelines, project structure & module organization, build, test, and development commands, workflow and coding style & naming conventions.
FluidAudio copilot-instructions.md
Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).
speech-swift AGENTS.md
Instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
liney AGENTS.md
Instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.
Starcat AGENTS.md
Instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律(每次写代码前必读,违反即返工), 🌿 git 分支与 worktree(强制), 🧭 主进度索引(每次开工前必读) and 状态符号(与功能实现总览.md 同步).