What is auRO-whisky-macOS-setup CLAUDE.md?

A set of instructions for the auRO-whisky-macOS-setup repository that maps where project knowledge and change history are stored.

Use it when investigating past work, decisions, or bug fixes by checking commit messages, Git notes, and the repository's other documented history sources.

It prevents agents from answering history or decision questions from an incomplete record by requiring them to check all four designated sources.

How jirukouya/auRO-whisky-macOS-setup configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jirukouya/auRO-whisky-macOS-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/jirukouya/auRO-whisky-macOS-setup/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jirukouya/auRO-whisky-macOS-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jirukouya/auro-whisky-macos-setup/claude-md/github.svg)](https://agentmods.dev/instructions/jirukouya/auro-whisky-macos-setup/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jirukouya/auro-whisky-macos-setup/claude-md"><img src="https://agentmods.dev/badge/instructions/jirukouya/auro-whisky-macos-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jirukouya/auro-whisky-macos-setup/claude-md"><img src="https://agentmods.dev/badge/instructions/jirukouya/auro-whisky-macos-setup/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,314 This file is loaded in full into every session.

When invoked 1,314 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.

Model	Per session	Once invoked
Fable 5.1	$0.01314	$0.01314
Opus 5.5	$0.00526	$0.00526
Sonnet 5.5	$0.00263	$0.00263
Haiku 4.5	$0.00131	$0.00131

Measured 1mo ago against content hash bfbfe313b11d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auRO-whisky-macOS-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 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.

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.

Project knowledge map

This file is an index, not content. Its only job: tell any reader (a fresh Claude Code/Codex session, the maintainer months from now, or an external contributor) where the actual information lives, so nothing gets missed by relying on memory alone.

Rule: before answering any "what have we already done / dealt with / decided about X" question for this project, check all four sources below — not just one or two.

The four places change history lives

git log (commit messages) — the most granular record, tied to each diff. Bug-fix/investigation commits should follow a Symptom / Ruled out / Root cause / Fix body structure (not just a one-line summary) — see the two best examples: commits 38092d5 and c1db2eb.

Also check git notes (git log --show-notes, or git notes show <hash>) — 13 older commits that predate this commit-message framework had that same Symptom/Ruled out/Root cause/Fix detail retroactively attached as notes instead of rewriting already-pushed history. Notes don't show up in a plain git log or a fresh git clone/git fetch — the ref (refs/notes/commits) has to be fetched explicitly: git fetch origin refs/notes/commits:refs/notes/commits, then git log --show-notes. Easy to forget this ref exists at all if you don't already know to look for it — which is exactly the kind of gap this file exists to close.
CHANGELOG.md — curated, per-version (Keep a Changelog format), human-facing "what changed and why" summary. This is the closest equivalent to a traditional changelog/troubleshooting summary — check it whenever comparing "what do we already have" against an external log or report.
SKILL.md (each step's mandatory verification blocks) and TROUBLESHOOTING.md ("Known open issues" + the Common Gotchas table, split out of SKILL.md at v0.19.0 — see "Standing constraints" below). Together these are the living current-state doc: symptoms, verification methods, and anything still unresolved. If a question is "is this still broken / how do we verify this," this is the first place to check, since it's the only layer that's actively kept in sync with the live install process.

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.

1mo ago Changed · -14 tokens per session bfbfe313b11d
1mo ago Changed · +1 tokens per session 51d11e27786c
2mo ago First seen · 97 lines · 1,327 tokens per session scan A 95cdfd6d1a26

Subscribe to this mod's changes

auRO-whisky-macOS-setup CLAUDE.md is an instructions file published in the GitHub repository jirukouya/auRO-whisky-macOS-setup (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,314 tokens to every session, about $0.0053 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.

auRO-whisky-macOS-setup CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
auRO-whisky-macOS-setup CLAUDE.mdjirukouya/auRO-whisky-macOS-setup	Instructions file	5	1mo ago	MIT	A	1,314	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

auRO-whisky-macOS-setup: Instructions file for Claude Code