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.
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.
curl -O https://raw.githubusercontent.com/cloudposse/atmos/main/.claude/skills/editions/SKILL.mdgit clone --depth 1 https://github.com/cloudposse/atmosWrote 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.
[](https://agentmods.dev/skills/cloudposse/atmos/editions)<a href="https://agentmods.dev/skills/cloudposse/atmos/editions"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/editions/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.
<a href="https://agentmods.dev/skills/cloudposse/atmos/editions"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/editions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00093 | $0.01798 |
| Opus 5.5 | $0.00037 | $0.00719 |
| Sonnet 5.5 | $0.00019 | $0.00360 |
| Haiku 4.5 | $0.00009 | $0.00180 |
Grade A, and why
editions 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 yesterday.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editions (Date-Anchored Defaults)
Source of truth: docs/prd/editions.md. This skill is the contributor-facing decision tree for
"does my change need edition handling", not a restatement of the architecture — read
docs/prd/editions.md for the four-layer model, pkg/edition/journal.go's Entry schema, and the
guardrail tests before touching anything. This skill exists because the deciding question
("does this default change supersede prior behavior?") is easy to answer wrong by only checking
the literal rule ("new keys are never journal-gated") without checking what the rule is for.
The decision tree
Ask these in order. Stop at the first "yes."
1. Does this change a previously-shipped key's literal default value?
(e.g. flipping settings.terminal.pager's struct default from "true" to "false".)
→ Yes: KindValue journal entry required. Follow docs/prd/editions.md's "Contributor
workflow" exactly:
- Change the literal in
setDefaultConfiguration(pkg/config/load.go), and indefaultCliConfig(pkg/config/default.go) if that struct also carries the field. Confirm the key isn't set in the embeddedatmos.yaml(layer (b) must stay journaled-key-free). - Append a dated
Entry{Date, Key, Kind: KindValue, Old, New, Description, Ref}topkg/edition/journal.go—Refis the PR URL,Old/Newtyped as the field is typed today. - Regenerate the snapshot:
ATMOS_REGENERATE_DEFAULTS_SNAPSHOT=true go test ./pkg/config -run TestDefaultConfigurationSnapshot.
Skipping this is not optional — pkg/config/default_snapshot_test.go fails the build on an
unjournaled value change.
2. Is this a brand-new key whose default doesn't change what Atmos already, unconditionally did? (e.g. a new opt-in flag for genuinely new functionality with no prior equivalent — nothing before this key ever did what it controls, not even as hardcoded behavior.)
→ No action needed. docs/prd/editions.md: "new defaults are never journal-gated." Only edit
the layer that introduces the key and regenerate the snapshot (new-key diffs there don't require a
journal entry, just committing the updated golden file).
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.
- yesterday Changed · -6 lines 455563c2937f
- 1mo ago First seen · 126 lines · 93 tokens per session scan A f1e9c0bd6b7c
editions is a skill published in the GitHub repository cloudposse/atmos (1,403 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 1,798 once invoked, about $0.0004 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 2026-09-15.
Other skills, from other repositories
gke-basics
Trigger: Use when working with Google Kubernetes Engine basics — cluster setup, node pools, workloads, networking, and storage fundamentals.
clum-mcp
A procedure for using clum, a remote Linux operations platform that runs commands through a secure proxy rather than direct SSH. It also describes how to inspect systems, investigate failures, compare solutions, and review incidents.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
x-nets
Enhanced netstat module with cached data and structured output. View network connections, routing tables, and interface statistics in interactive or TSV/CSV formats. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
x-osv
CLI for Google OSV database. Query vulnerabilities for packages, scan local projects for vulnerable dependencies. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill). Required Tool: Install osv-scanner for project scanning (see https://github.com/google/osv-scanner).
x-uptime
Enhanced uptime with structured YAML output showing uptime, users, and 1/5/15-minute load averages. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.