atmos: Skill for Claude Code

.claude/skills/homebrew/SKILL.md

homebrew is a skill for Claude Code from cloudposse/atmos. It costs 126 tokens per session (2,786 once invoked), scanned B, original, Apache-2.0.

A step-by-step guide for preparing and submitting a Homebrew formula pull request for atmos. Homebrew is a package manager for macOS and Linux, and a formula describes how to build and install a program.

In plain words
What is it for?
Use it to check an existing pull request, fill in Homebrew's current template, keep the commit subject within its limit, and run installation, test, and audit commands before submission.
Why use it?
It helps avoid automatic closure caused by an incomplete pull-request template, missing AI disclosure, duplicate submissions, or failed checks.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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

About the project

Atmos is an infrastructure runtime that coordinates tools such as Terraform, OpenTofu, Kubernetes, Helm, Packer, Ansible, and containers through consistent commands and configuration. It is for teams running cloud infrastructure on laptops, in CI, or through AI agents across environments and regions. Its catalogue entries provide skills, agents, commands, and other add-ons for Atmos workflows.

cloudposse/atmos · 1,403 stars · on GitHub · atmos.tools

Reuse

Borrowing it

Nothing to install: this file belongs to cloudposse/atmos. 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/cloudposse/atmos/main/.claude/skills/homebrew/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cloudposse/atmos

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 homebrew

README.md
[![agentmods](https://agentmods.dev/badge/skills/cloudposse/atmos/homebrew/github.svg)](https://agentmods.dev/skills/cloudposse/atmos/homebrew)
Your own site
<a href="https://agentmods.dev/skills/cloudposse/atmos/homebrew"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/homebrew/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 homebrew

Your own site · 80×15
<a href="https://agentmods.dev/skills/cloudposse/atmos/homebrew"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/homebrew.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,786 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00126 $0.02786
Opus 5.5 $0.00050 $0.01114
Sonnet 5.5 $0.00025 $0.00557
Haiku 4.5 $0.00013 $0.00279

Measured 1mo ago against content hash 95cc1acd7c5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

homebrew scanned grade B with 1 finding 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$tap_dir"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/skills/homebrew/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Homebrew Formula PR Workflow (atmos)

Use this skill for any change to Formula/a/atmos.rb in Homebrew/homebrew-core (a different repo than cloudposse/atmos — all gh commands below need --repo Homebrew/homebrew-core). It exists because a previous attempt got auto-closed by BrewTestBot for looking AI-generated and skipping the real template — this skill is how to not repeat that.

Do not open a new PR to fix a closed one

If BrewTestBot closes a PR with the incomplete-pr-template message, it says explicitly: "Do not open a new pull request for this." Editing the body of the existing (closed) PR to complete the template makes the bot reopen it automatically. Check state first:

gh pr view <num> --repo Homebrew/homebrew-core --json state,title,body,comments

Before submitting anything, also confirm there isn't a duplicate open PR for the same formula (the template's own checklist requires this):

gh pr list --repo Homebrew/homebrew-core --search "atmos in:title" --state open --json number,title,url

The real PR template

Fetch it fresh rather than assuming — it changes:

gh api repos/Homebrew/homebrew-core/contents/.github/PULL_REQUEST_TEMPLATE.md --jq '.content' | openssl base64 -d -A

The template body is just the checklist — unlike atmos's own PR template, there are no ## what/## why headers. That does not mean explanation is optional: real merged homebrew-core PRs consistently open with a free-text paragraph (often with links to the upstream fix/issue) above the checklist — e.g. "Fixes #301233 by building libraries statically... Roughly similar to Fedora's layout, but they also delete the Flang RT headers..." (PR #301251). Write that explanation; just don't force it into headed sections the template doesn't ask for. The checklist itself is what BrewTestBot actually gates on. As of this writing, the checklist covers:

  • Followed the contributing guidelines?
  • Commits follow the commit style guide?
  • No other open PR for the same formula?
  • Built locally with HOMEBREW_NO_INSTALL_FROM_API=1 brew install --build-from-source <formula>?
  • brew test <formula> passing?
  • brew audit --strict <formula> passing (or brew audit --new for a new formula)?
  • AI/LLM disclosure checkbox (see below — this is the one that sank the first attempt).

Read the full file on GitHub · 229 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. 1mo ago First seen · 229 lines · 126 tokens per session scan B 95cc1acd7c5c

Subscribe to this mod's changes

homebrew is a skill published in the GitHub repository cloudposse/atmos (1,403 stars, last pushed today), licensed Apache-2.0. It adds 126 tokens to every session and 2,786 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.