atmos: Instructions file for Claude Code

CLAUDE.md

atmos CLAUDE.md is an instructions file for Claude Code from cloudposse/atmos. It costs 6,165 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Atmos, a Go command-line tool for managing cloud infrastructure. They cover the project structure, mandatory Git worktrees, concurrent work, and maintenance practices.

In plain words
What is it for?
Use them when working on Atmos code, especially while navigating worktrees, handling parallel sessions, or maintaining pull requests.
Why use it?
They prevent agents from inspecting the wrong worktree or making changes without following the repository's development rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

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 · 1,405 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.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 atmos CLAUDE.md

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

agentmods 80×15 button for atmos CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cloudposse/atmos/claude-md"><img src="https://agentmods.dev/badge/instructions/cloudposse/atmos/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,165 This file is loaded in full into every session.
When invoked 6,165 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06165 $0.06165
Opus 5.5 $0.02466 $0.02466
Sonnet 5.5 $0.01233 $0.01233
Haiku 4.5 $0.00617 $0.00617

Measured today against content hash c014e05a1729, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

atmos 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 today.

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 · 455 lines

How it starts

The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working with this repository.

Project Overview

Atmos: Go CLI for cloud infrastructure orchestration via Terraform/Helmfile/Packer with stack-based config, templating, policy validation, vendoring, and terminal UI.

Git Worktrees (MANDATORY)

This repository uses git worktrees for parallel development. When working in a worktree:

  • ALWAYS stay within the current working directory - Never escape to parent directories
  • Use relative paths or paths under the current working directory - Do not hardcode /Users/*/atmos/ paths
  • The worktree IS the repository - All files, including pkg/, cmd/, internal/, exist within the worktree
  • Never assume the parent directory is the repo - Worktrees like .conductor/branch-name/ are complete, independent working copies

Why this matters: Searching outside the worktree will find stale code from the main branch instead of the current branch's code. This leads to incorrect analysis and recommendations.

For Task agents: When searching for files, always use the current working directory (.) or relative paths. Never construct absolute paths that might escape the worktree.

Concurrent Sessions (MANDATORY)

Multiple Claude sessions may be working on the same branch or worktree simultaneously. To avoid destroying other sessions' work:

  • NEVER delete, reset, or discard files you didn't create - Other sessions may have created them
  • NEVER run git reset, git checkout --, or git clean without explicit user approval
  • NEVER run go clean. In particular, go clean -cache deletes the shared Go build cache and breaks concurrent builds; it is not an approved troubleshooting step.
  • ALWAYS ask the user before removing untracked files - They may be work-in-progress from another session
  • When you see unfamiliar files, assume another session created them - ask the user what to do
  • If pre-commit hooks fail due to files you didn't touch, ask the user how to proceed rather than trying to fix or remove them

Read the full file on GitHub · 455 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. today Changed · +22 tokens per session c014e05a1729
  2. 6d ago Changed · +2 lines · +30 tokens per session 36775d21ba42
  3. 1mo ago Changed · -1 tokens per session 766d300e3ec9
  4. 1mo ago Changed b104bb71d08b
  5. 1mo ago Changed · -1 tokens per session 868477c9b272
  6. 1mo ago First seen · 453 lines · 6,115 tokens per session scan A 54f945dcd765

Subscribe to this mod's changes

atmos CLAUDE.md is an instructions file published in the GitHub repository cloudposse/atmos (1,405 stars, last pushed today), licensed Apache-2.0. It adds 6,165 tokens to every session, about $0.0247 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 2026-08-30.

Related

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).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,384 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens