Agent skill

Atmos Steps

by cloudposse in cloudposse/atmos

Shared Atmos step DSL for workflows, custom commands, hooks, and cast recordings: step types, env, output, workingdirectory, retry, and native alternatives to shell glue

Apache-2.0Auto-check passedDevOps & Cloud

Install Atmos Steps

skills CLI
$ npx skills add cloudposse/atmos --skill atmos-steps -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cloudposse/atmos atmos-steps --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cloudposse/atmos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-skills/skills/atmos-steps .claude/skills/atmos-steps && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
atmos-steps
GitHub stars
1.4k
Token cost
~2.3k tokens
SKILL.md length
1,032 words
Files
1
Skills in repo
70
Repo updated
First seen
Licence
Apache-2.0

At a glance

Shared Atmos step DSL for workflows, custom commands, hooks, and cast recordings: step types, env, output, workingdirectory, retry, and native alternatives to shell glue

  • DevOps & Cloud work in your project
  • SKILL.md covers Core Model, Where Steps Run, Common Fields and Step Types, plus 7 more sections
  • Calls python3

What it does

Atmos Steps is an agent skill from cloudposse/atmos. Shared Atmos step DSL for workflows, custom commands, hooks, and cast recordings: step types, env, output, workingdirectory, retry, and native alternatives to shell glue

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud. The repository describes itself as: Atmos is the open-source runtime for infrastructure — it builds, authenticates, and ships Terraform, OpenTofu, Packer, Ansible, Kubernetes, Helm, and containers the same way on… The licence is Apache-2.0.

When your agent uses it

  • DevOps & Cloud work in your project

Example prompts

  • “/atmos-steps”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 36726ae. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • atmos.tools

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Atmos Steps loads about 2.3k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 1,032 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cloudposse/atmos at commit 36726ae, republished under its Apache-2.0 licence (© cloudposse). 1,032 words, ~2,327 tokens.

Download SKILL.mdSave it as .claude/skills/atmos-steps/SKILL.md (or your agent's skills folder).
name
atmos-steps
description
Shared Atmos step DSL for workflows, custom commands, hooks, and cast recordings: step types, env, output, working_directory, retry, and native alternatives to shell glue
metadata.copyright
Copyright Cloud Posse, LLC 2026
metadata.version
1.0.0
metadata.category
ci-automation

Atmos Steps

Atmos steps are the shared execution DSL used by workflows, custom commands, hooks (kind: step), and cast recordings. When a task involves steps:, step type, working_directory, env, output, retries, or hook with: payloads, use this skill together with the surface-specific skill (atmos-workflows, atmos-custom-commands, or atmos-hooks).

Core Model

A step is a typed action with native fields. Do not treat steps as a place to write shell scripts by default. Prefer the Atmos field that expresses the operation directly:

  • Use working_directory instead of cd for real execution. A type: simulate child of a mode: steps cast may display cd <directory> to narrate a directory transition, but it never changes the working directory of later real steps.
  • Use env maps instead of inline FOO=bar command or export.
  • Use output: none instead of redirecting to /dev/null.
  • Use type: script instead of heredoc shell snippets like python3 - <<'PY'.
  • Use type: workdir with source and reset instead of mkdir, rm -rf, and cp.
  • Use type: atmos for Atmos commands instead of shelling out to atmos ... when the surface supports typed steps.
  • Use Atmos Terraform/OpenTofu rc configuration instead of hand-managing temporary .terraformrc or .tofurc files.

Shell is still valid for real shell work, but it should be a conscious fallback when no native step type or field expresses the intent.

Where Steps Run

Step fields are shared, but defaults differ by surface:

  • Workflows default command steps to type: atmos.
  • Custom command string steps historically behave like shell commands; use structured step objects when you need typed behavior.
  • Hooks use an envelope plus with:. For kind: step, the hook's type selects the step type, while with: contains the step-specific fields.
  • Cast steps can run nested steps and record their terminal output.

Always load the surface-specific skill for invocation rules, path anchoring, and template context.

Common Fields

Most typed steps can use these fields when the step type supports them:

yaml
steps:
  - name: validate
    type: script
    interpreter: python3
    working_directory: !repo-root .
    env:
      ATMOS_LOGS_LEVEL: warn
    output: none
    retry:
      max_attempts: 3
      delay: 2s
    script: |
      print("ok")

Important shared fields:

  • name: Stable step id for logs, dependencies, outputs, and resume behavior.
  • type: Registered step handler; the canonical catalog below is the source for authored YAML.
  • command: Command text for command-running steps.
  • script and interpreter: Inline script body and runtime for type: script.
  • working_directory: Directory for the subprocess or script.
  • env: Map of environment variables layered onto the step.
  • output: Output mode: raw, log, viewport, or none; test groups instead use failures or all.
  • retry: Retry policy around the whole step.
  • identity: Atmos identity used when the step runs.
  • when: Declarative condition for whether the step runs.
  • needs: Dependency names for concurrent control steps.
  • timeout: Duration limit for supported steps.
  • tty and interactive: Terminal handoff for commands that need it.

Step Types

Use atmos.tools/workflows/steps/type and its type-specific subpages (e.g. atmos.tools/workflows/steps/type/shell) as the canonical reference. Current canonical step types include:

  • Command and integration: atmos, shell, script, exec, container, emulator, http, archive, require, workdir, cast, store.
  • Orchestration: test, parallel, matrix, wait, wait-all, cancel.
  • Interactive: input, confirm, choose, filter, file, write.
  • UI and output: toast, markdown, spin, table, pager, format, join, style, log, junit, hint, alert, say, title, clear, linebreak, stage, sleep, env, exit.

Use webhook only as the http alias and assert only as the require alias; document and configure the canonical names unless compatibility requires an alias.

If code and docs disagree, inspect the registered step handlers under pkg/runner/step/ and schema constants in pkg/schema/task.go.

For smoke tests and integration checks, use atmos-tests for test groups, assertions, parallel dependencies, and matrix cases.

Environment

Prefer map syntax:

yaml
env:
  PATH: '{{ env "PWD" }}/../../.context/bin:{{ env "PATH" }}'
  ATMOS_LOGS_LEVEL: warn

For custom commands, command-level env supports the same map style. Use template expressions such as {{ env "PATH" }} or .Env where supported. Use valueCommand only when the value genuinely must come from a command's stdout; do not move shell string building into valueCommand.

Show full SKILL.md (420 more words)Show less

Working Directory

Use working_directory at the narrowest useful scope:

yaml
steps:
  - name: docs
    type: shell
    working_directory: !repo-root .
    command: npm run docs:build

Do not use --chdir or cd for real workflow, custom-command, or step execution when working_directory can express the same thing. In a mode: steps cast, a display-only type: simulate cd <directory> is the exception: use it to keep the recorded story coherent, and still configure working_directory on every real step. Relative paths must be checked against the surface's base path rules.

Working-directory resolution is not one rule — it differs by surface, and getting this wrong silently anchors relative fields (source, destination, path, files, context, ...) to the wrong directory instead of erroring:

SurfaceRelative working_directory resolves against
Custom command's own working_directory: (command- or step-level)Atmos base_path — always, whether or not the value starts with ./
A workflow's own working_directory: (the workflow-level default), or a type: shell/exec/atmos step's working_directory:Atmos base_path — always, whether or not the value starts with ./
An extended/registered step type (archive, file, junit, workdir, container, ...) with its own step-level working_directory:The current working directory — always, whether or not the value starts with ./
kind: step/kind: steps hookThe component's own working directory for a bare value or when unset; the current working directory for a dot-prefixed value (., .., ./x, ../x) — see atmos-hooks for the full Dot/Bare rule

A workflow-level working_directory: default still reaches extended step types that leave their own working_directory: unset — it falls back to the same base_path-anchored resolution the workflow-level default already gets for shell/exec/atmos steps.

After working_directory is resolved, relative handler fields such as source, destination, path, files, and context resolve against that directory. For container builds, Dockerfile resolves relative to the resolved context, not directly to working_directory.

Output

Use output modes instead of pipe redirection:

yaml
steps:
  - name: prepare
    type: atmos
    command: terraform generate varfile vpc -s dev
    output: none

output: none is for quiet setup. raw preserves command output, log routes through Atmos logging, and viewport is for richer terminal display.

Script Steps

Use type: script for inline scripts:

yaml
steps:
  - name: validate-cast
    type: script
    interpreter: python3
    script: |
      from pathlib import Path

      text = Path("path/to/your.cast").read_text()
      if "All proofs passed" not in text:
          raise SystemExit("cast validation failed")

Do not put command on a script step. The schema requires interpreter and script.

Workdir Steps

Use type: workdir for repeatable scratch directories:

yaml
steps:
  - name: stage-fixtures
    type: workdir
    path: .context/casts/demo
    source: demo/casts/fixtures
    reset: true

This replaces shell sequences that create, delete, and copy directories.

Hooks

For hooks, the hook envelope controls lifecycle behavior and with: is the step payload. A scaffold template may use this bridge too, but only with kind: step or kind: steps and its two generation events:

yaml
hooks:
  notify:
    kind: step
    type: http
    events: [after.terraform.apply]
    on_failure: warn
    retry:
      max_attempts: 3
    with:
      url: https://example.com/hook
      method: POST

Use atmos-hooks for hook events, outcome conditions, on_failure, and preflight behavior.

Verification

When changing step YAML, verify the user-facing command from the directory where users actually run Atmos. Prefer working_directory fields in YAML and command tool workdir settings in tests over shell cd or --chdir.

© cloudposse, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in agent-skills/skills/atmos-steps of cloudposse/atmos.

Open the folder on GitHubat commit 36726ae

Compare with similar skills

Atmos Steps next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Atmos Steps compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Atmos Steps this skillcloudposse/atmos1.4k—~2.3kAutomated safety check: PassApache-2.0
Monitor CInrwl/nx29k6 repos~4.7kAutomated safety check: PassMIT
Terraform and OpenTofu Guideagentscope-ai/QwenPaw35k6 repos~4.2kAutomated safety check: PassApache-2.0
Vercel Optimize Auditvercel-labs/agent-skills32k9 repos~4.3kAutomated safety check: PassNone
Openclaw Live Updateropenclaw/openclaw392k—~3.7kAutomated safety check: PassMIT
Analyze GitHub Action Logswithastro/astro63k1 repos~1.3kAutomated safety check: PassCustom licence

Similar skills

  • Monitor CI

    nrwl/nx

    Monitor Nx Cloud CI pipeline and handle self-healing fixes. An agent skill from nrwl/nx.

    29k GitHub starsUsed in 6 repos~4.7k tokens
    DevOps & CloudAuto-check passed
  • Terraform and OpenTofu Guide

    agentscope-ai/QwenPaw

    Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.

    35k GitHub starsUsed in 6 repos~4.2k tokens
    DevOps & CloudAuto-check passed
  • Vercel Optimize Audit

    vercel-labs/agent-skills

    Official

    Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.

    32k GitHub starsUsed in 9 repos~4.3k tokens
    DevOps & CloudAuto-check passed
  • Openclaw Live Updater

    openclaw/openclaw

    Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.

    392k GitHub stars~3.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Official

    Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements.

    63k GitHub starsUsed in 1 repo~1.3k tokens
    DevOps & CloudAuto-check passed
  • Creates and queries KubeSphere users, workspaces and projects and assigns built-in roles, defaulting to least privilege and never deleting anything.

    17k GitHub starsUsed in 1 repo~3.1k tokens
    DevOps & CloudAuto-check passed

More from cloudposse/atmos

All 70 skills in this repo
  • Fix Log

    cloudposse/atmos

    A skill your agent uses when implementing, finishing, documenting, or reviewing a fix, repair, remediation, bug fix, debug-and-fix task, workflow fix, infrastructure fix, or any change that should…

    1.4k GitHub stars~685 tokensUpdated yesterday
    Auto-check passed
  • Atmos Lint

    cloudposse/atmos

    Atmos Terraform linting with TFLint: standalone atmos terraform lint, component-aware config discovery and toolchain versions, TFLint rule configuration, and lifecycle hooks/CI findings.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Changelog

    cloudposse/atmos

    Blog post authoring for Atmos: MDX template, frontmatter, website/blog/tags.yml and authors.yml rules, problem-first framing, backtick-opening ban, optional cast embeds, and no-Go-internals leakage.

    1.4k GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed
  • Editions

    cloudposse/atmos

    Decide whether a PR's new or changed default needs edition-journal handling (pkg/edition, docs/prd/editions.md), and do the mechanical work if so: journal entries, the four-layer default check…

    1.4k GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Atmos Migration

    cloudposse/atmos

    Migrate to Atmos from native Terraform, Terraform Workspaces, Terramate, Terragrunt, Make, Just, or Task; migrate tool versions from mise or Aqua CLI; migrate AWS/GCP/Azure CLI configs, Leapp…

    1.4k GitHub stars~5.1k tokensUpdated yesterday
    Auto-check: warnings
  • PR Maintenance Loop

    cloudposse/atmos

    Start an hourly background loop that keeps the current branch's PR rebased, its addressed CodeRabbit threads resolved, its CI checks passing, its lint clean, its tests passing with adequate patch…

    1.4k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Atmos Steps

What does Atmos Steps do?

Shared Atmos step DSL for workflows, custom commands, hooks, and cast recordings: step types, env, output, workingdirectory, retry, and native alternatives to shell glue. Atmos Steps is an agent skill from cloudposse/atmos.

When should I use Atmos Steps?

Atmos Steps fits situations like: devOps & Cloud work in your project.

How do I install Atmos Steps in Claude Code?

Run `npx skills add cloudposse/atmos --skill atmos-steps -a claude-code`. Or copy the skill folder (agent-skills/skills/atmos-steps in cloudposse/atmos) into .claude/skills/atmos-steps in your project. Claude Code loads it when a task matches its description.

How do I install Atmos Steps in Codex?

Run `npx skills add cloudposse/atmos --skill atmos-steps -a codex`. Or copy the skill folder (agent-skills/skills/atmos-steps in cloudposse/atmos) into .agents/skills/atmos-steps in your project. Codex loads it when a task matches its description.

Can I use Atmos Steps in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cloudposse/atmos --skill atmos-steps -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/atmos-steps, .gemini/skills/atmos-steps, .github/skills/atmos-steps and .opencode/skills/atmos-steps in your project.

What does Atmos Steps need to run?

Going by SKILL.md and its folder, Atmos Steps needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Atmos Steps access the network?

SKILL.md names 1 domain. As links in the text: atmos.tools. This is read from the text; nothing was executed.

Is Atmos Steps safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Atmos Steps use?

Atmos Steps is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Atmos Steps use?

About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Atmos Steps?

Skills that share tags, products or a category with Atmos Steps: Monitor CI (nrwl/nx, 29k stars), Terraform and OpenTofu Guide (agentscope-ai/QwenPaw, 35k stars), Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars) and Openclaw Live Updater (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Atmos Steps?

cloudposse (a GitHub organization) maintains it in cloudposse/atmos, which has 1,396 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 8, 2026.

Source: cloudposse/atmos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.