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/agents-mdgit clone --depth 1 https://github.com/ben196888/mac-set-upWhat 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 | $0.00558 | $0.00558 |
| Opus 5 | $0.00279 | $0.00279 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
mac-set-up AGENTS.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 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.
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.
AGENTS.md
This file provides guidance to Codex 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, AI coding tools, and system preferences.
Running
chmod +x install.sh
./install.sh
Individual scripts can also be run directly, for example ./languages/python.sh or ./agentic/agentic_skills.sh --codex.
There are no build, lint, or test commands. This is a shell-based installer with no automated test suite.
Architecture
install.sh is the orchestrator and executes the other scripts in order:
essential.sh- Xcode CLT, Rosetta 2, Homebrew with Apple Silicon vs Intel path detectioncli_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/- Per-language setup scripts for .NET, Go, Java, JavaScript, LaTeX, Python, Rustides.sh- VS Code, Cursorbrowsers.sh- Firefox, Chrome, Edge, DuckDuckGodevtools.sh- OrbStack, kubectl, Postman, Google Cloud SDK, ChatGPT, Claude Code, Playwright CLIagentic/install.sh- Agentic instructions, skills, and MCP setuptools.sh- AppCleaner, Spotify, Slack, Messenger, Signal, Discord, Rectanglemacos.sh- System defaults such as Dock, trackpad, keyboard, and Spotlight configuration
Key Conventions
- Always use the
BREW_PREFIXvariable fromessential.shinstead of hardcoding Homebrew paths. - Config files live alongside their installers and are copied into place. Do not switch this repo to symlink-based setup.
- Manage reusable agent setup through
agentic/install.sh; configuration lives inagentic/agentic.conf. - Shell profile additions should be conditional so a missing tool does not break the shell.
- Prefer
cpandcp -rfor installation steps.
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.
- 2d ago First seen · 44 lines · 558 tokens per session scan A 35df48dd750f
mac-set-up AGENTS.md is an instructions file published in the GitHub repository ben196888/mac-set-up (11 stars, last pushed 23d ago), licensed MIT. It adds 558 tokens to every session, about $0.0028 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.
Applite CLAUDE.md
Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.
wispterm AGENTS.md
Instructions for xuzhougeng/wispterm, covering agents.md, architecture, ui presentation styles, cohesion and coupling and integration layer vs feature domains.
HomeClaw AGENTS.md
Instructions for omarshahine/HomeClaw, covering homeclaw, architecture, project structure, build system and xcode version.
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.
best-claude-hud AGENTS.md
Instructions for GaoSSR/best-claude-hud, covering project agent instructions and release work.