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/cknadler/setup/claude-mdgit clone --depth 1 https://github.com/cknadler/setupWhat 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 | $0.01067 | $0.01067 |
| Opus 5 | $0.00534 | $0.00534 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
setup CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
setup
Bootstrap a fresh macOS dev environment.
Layout
bootstrap— entrypoint: argument parsing, logging, step orchestration.lib.sh— step functions (step_xcode,step_homebrew, …), logging (log_info,log_warn, …), state tracking (state_*), and read-only doctor probes (doctor_*). Sourced bybootstrap.Brewfile— default packages installed on every machine, including the everyday apps (Signal, Spotify, Dropbox, Obsidian, …) andmasHEIC.Brewfile.home— home-machine extras (Discord, VLC, Synology Drive, …); auto-installed when "personal" is chosen.Brewfile.media— media apps (Plex, YACReader).Brewfile.music— audio production. Out of scope for current work..osx—defaults writecustomizations; run last (some changes require a restart).Makefile—make test,make lint,make doctor,make all.tests/— bats-core test suite (63 tests) using PATH-shim mocks undertests/fixtures/bin/. Tests sourcelib.shdirectly and exercise step functions with isolated$HOMEand 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.
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 · 97 lines · 1,067 tokens per session scan A 1af7dbf5d4b1
setup CLAUDE.md is an instructions file published in the GitHub repository cknadler/setup (10 stars, last pushed 2mo ago), licensed MIT. It adds 1,067 tokens to every session, about $0.0053 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.