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-workflowsWrote 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-workflows)<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-workflows"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-workflows.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01244 |
| Opus 5 | $0.00024 | $0.00622 |
| Sonnet 5 | $0.00010 | $0.00249 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
atmos-workflows 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 2d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atmos Workflows
Use this skill for reusable orchestration in workflows: files: multi-step deployment flows,
parallel or matrix execution, cross-component operations, preconditions, retries, typed UI/output
steps, container/emulator steps, and workflow-level dependencies.
When a task is primarily about shared step fields (type, working_directory, env, output,
retry, script, workdir, or hook with: payloads), also load atmos-steps.
For full workflow syntax, read references/workflow-syntax.md.
Quick Shape
workflows:
deploy-network:
description: Deploy network components
stack: plat-ue2-dev
steps:
- type: atmos
command: terraform deploy vpc
- type: atmos
command: terraform deploy dns
atmos workflow deploy-network
atmos workflow deploy-network --stack plat-ue2-prod
Discovery
Workflow files live under workflows.base_path in atmos.yaml.
workflows:
base_path: stacks/workflows
When --file is omitted, Atmos scans workflow files and runs the workflow if exactly one match is
found. Use --file for ambiguous workflow names.
Step Type Guidance
Use native step types when they express the intent directly:
| Need | Prefer |
|---|---|
| Run Atmos | type: atmos |
| Shell/process execution | shell or exec |
| Concurrent execution | parallel, matrix |
| Background services and waits | background: true, wait, wait-all |
| Preconditions | require / assert |
| Retry transient failures | retry |
| Containers and emulators | container, emulator |
| HTTP calls | http |
| User-facing output | say, toast, markdown, table, pager, format, spin, stage |
| Workflow recordings | cast, simulate via atmos-cast |
Shell is appropriate for short glue, terminal-native tools, or checked-in scripts. Large inline shell blocks with loops, sleeps, formatting, CI metadata, or hand-rolled parallelism should usually be replaced by native workflow steps.
What ships with it
1 file 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.
- 2d ago First seen · 178 lines · 49 tokens per session scan A 33940011f694
atmos-workflows is a skill published in the GitHub repository cloudposse/atmos (1,372 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 1,244 once invoked, about $0.0002 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
gws-tasks
Google Tasks: Manage task lists and tasks.
persona-customer-support
Manage customer support — track tickets, respond, escalate issues.
recipe-create-doc-from-template
Copy a Google Docs template, fill in content, and share with collaborators.
recipe-create-events-from-sheet
Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.
recipe-create-shared-drive
Create a Google Shared Drive and add members with appropriate roles.
recipe-create-task-list
Set up a new Google Tasks list with initial tasks.