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-custom-commandsWrote 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-custom-commands)<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-custom-commands"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-custom-commands.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01094 |
| Opus 5 | $0.00019 | $0.00547 |
| Sonnet 5 | $0.00008 | $0.00219 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
atmos-custom-commands 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 4d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atmos Custom Commands
Use this skill when users define or modify project-specific Atmos CLI commands in the top-level
commands section of atmos.yaml.
Custom commands replace scattered scripts with discoverable CLI commands that can use arguments, flags, environment variables, authentication identities, tool dependencies, component config, nested subcommands, and typed execution steps.
When a task is mainly about steps, step type, working_directory, step env, output,
scripts, workdirs, or hook-compatible step payloads, also load atmos-steps.
Quick Shape
commands:
- name: hello
description: Say hello
arguments:
- name: name
default: World
steps:
- type: say
text: "Hello {{ .Arguments.name }}"
atmos hello
atmos hello Erik
For full field syntax, read references/command-syntax.md.
Agent Workflow
- Inspect existing
commandsinatmos.yamland imported config before adding a new command. - Prefer native typed steps over large shell blocks.
- Add flags and arguments with clear names and defaults.
- Use
dependencies.toolsfor tools the command needs in its execution context. - Use
identitywhen the command needs Atmos Auth credentials. - Verify with
atmos <command> --helpand a dry-run or read-only invocation when possible.
Native Step Preference
Default to structured steps before shell:
| Need | Prefer |
|---|---|
| Run an Atmos command | type: atmos |
| Operator messages | say, toast, markdown, table, pager |
| Data shaping | format, join, filter, write |
| Status/progress | spin, stage, log, linebreak |
| Concurrency | parallel, matrix, wait, wait-all |
| Containers/emulators | container, emulator |
| HTTP calls | http |
| Preconditions | require / assert |
| External command glue | shell / exec |
Shell is still appropriate for short glue commands, terminal-native tools, checked-in scripts, or commands that genuinely need shell semantics.
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.
- 4d ago First seen · 161 lines · 39 tokens per session scan A a6c547264310
atmos-custom-commands is a skill published in the GitHub repository cloudposse/atmos (1,372 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 1,094 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-drive
Google Drive: Manage files, folders, and shared drives.
gws-chat
Google Chat: Manage Chat spaces and messages.
gws-gmail-reply
Gmail: Reply to a message (handles threading automatically).
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-gmail-watch
Gmail: Watch for new emails and stream them as NDJSON.
gws-calendar-insert
Google Calendar: Create a new event.