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.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cloudposse/atmosnpx agentmods add skills/cloudposse/atmos/atmos-scaffoldWrote 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/atmos-scaffold)<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-scaffold"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-scaffold/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/atmos-scaffold"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-scaffold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.03129 |
| Opus 5 | $0.00026 | $0.01564 |
| Sonnet 5 | $0.00010 | $0.00626 |
| Haiku 4.5 | $0.00005 | $0.00313 |
Grade A, and why
atmos-scaffold 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 5d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atmos Scaffold
Use this skill for generating boilerplate (components, configs, directory structures)
from templates via atmos scaffold generate, for authoring new templates
(scaffold.yaml), and for updating previously-generated output from a changed
template via --update.
For bootstrapping a brand-new Atmos project from the built-in template catalog, load
atmos-init instead — it shares this exact engine but has its own command surface and
built-in template list.
Quick Shape
apiVersion: atmos/v1
kind: AtmosScaffoldConfig
metadata:
name: terraform-component
description: Standard Terraform component structure
spec:
fields:
- name: component_name
label: Name of the component
type: input
required: true
atmos scaffold generate terraform-component ./components/terraform/vpc
atmos scaffold list
atmos scaffold validate ./components/terraform/vpc/scaffold.yaml
atmos scaffold ships experimental — behavior may change between releases.
Creating a Template
A template is a directory containing scaffold.yaml (the questionnaire and
optional conditional-generation/hooks config) plus the files to generate.
Files are auto-discovered by walking the template directory — there is no
files: manifest listing every file (spec.files: exists only for the optional
conditional-generation overlay, see below).
Mark a file as a Go template (rendered with the collected answers) either by:
- Naming it with a
.tmplextension, or - Adding an
atmos:templatemagic comment in the first 10 lines, in the comment style matching the file type:# atmos:template(shell/YAML/Python),// atmos:template(Go/JS/C++),/* atmos:template */(C-style block),<!-- atmos:template -->(HTML/XML/Markdown)
Template sources: embedded (built into the Atmos binary), custom (declared under
scaffold.templates in atmos.yaml), or catalog/remote (git/https/s3/oci — advertised
as stubs, fetched on selection). An OCI source (oci://ghcr.io/org/template:v1) is pulled
via the same pkg/oci client atmos vendor pull reuses (load atmos-vendoring for the
URL syntax and auth precedence). --ref only applies to git sources; OCI/S3/local sources
address a version through the source string itself.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 286 lines · 52 tokens per session scan A a90fcc93ef85
atmos-scaffold is a skill published in the GitHub repository cloudposse/atmos (1,374 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 3,129 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
trigger-cost-savings
Analyze Trigger.dev tasks, schedules, and runs for cost optimization opportunities. Use when asked to reduce spend, optimize costs, audit usage, right-size machines, or review task efficiency. Combines static source analysis with live run analysis via the Trigger.dev MCP tools (listruns, getrundetails…
vs-project
Create Viking web projects, start and verify a local preview, or deploy a generated project to Volcengine IGA Pages when explicitly requested. Includes agent-guided feature, eligible application, dataset, scene, and authentication choices. Use only after confirming the installed CLI exposes vs project; otherwise stop…
kastell-ops
Kastell CLI patterns, architecture, anti-patterns, and decision trees. Use automatically when working in Kastell codebase or when asked about Kastell server infrastructure, security audit, hardening, lock, provision, or provider management.
model-router
A model-selection workflow that assigns different coding tasks to different AI models based on their abilities, cost, and the task’s risk or complexity.
cloud-push-quarantine
Inspect and recover rows isolated by cloud push after a server rejection, without exposing row contents. Use when sync-health reports pushquarantine.
new-gh-issue-orchestration
Orchestrates a GitHub-issue-driven delivery workflow from issue intake to PR creation using reviewer-first then worker execution. Invoked when the user provides a GitHub issue link/number and asks to start end-to-end delivery.