Agent skill

Atmos Toolchain

by cloudposse in cloudposse/atmos

Toolchain management: declarative dependencies, automatic installs, install/exec/search/env commands, Aqua registry integration, version pinning, package verification

Apache-2.0Auto-check passedDevOps & Cloud

Install Atmos Toolchain

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

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

GitHub CLI
$ gh skill install cloudposse/atmos atmos-toolchain --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-toolchain .claude/skills/atmos-toolchain && 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-toolchain
GitHub stars
1.4k
Token cost
~3.9k tokens
SKILL.md length
1,401 words
Files
2 (incl. references)
Skills in repo
70
Repo updated
First seen
Licence
Apache-2.0

At a glance

Toolchain management: declarative dependencies, automatic installs, install/exec/search/env commands, Aqua registry integration, version pinning, package verification

  • Works in 5 steps: CLI flags (highest) → Environment variables → atmos.yaml configuration → …
  • DevOps & Cloud work in your project
  • SKILL.md covers Purpose, Default Rule, Core Concepts and Configuration in atmos.yaml, plus 9 more sections
  • Reaches github.com; needs ATMOS_GITHUB_TOKEN and GITHUB_TOKEN

What it does

Atmos Toolchain is an agent skill from cloudposse/atmos. Toolchain management: declarative dependencies, automatic installs, install/exec/search/env commands, Aqua registry integration, version pinning, package verification

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/commands-reference.md`).

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-toolchain”

Requirements

  • A credential in ATMOS_GITHUB_TOKEN
  • A credential in GITHUB_TOKEN

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. CLI flags (highest)
  2. Environment variables
  3. atmos.yaml configuration
  4. XDG data directory
  5. .tools fallback

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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and bash).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ATMOS_GITHUB_TOKEN
    • GITHUB_TOKEN

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

Context cost

Atmos Toolchain loads about 3.9k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 46 tokens; SKILL.md has 1,401 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
~3.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.7k

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). 1,401 words, ~3,926 tokens.

Download SKILL.mdSave it as .claude/skills/atmos-toolchain/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
atmos-toolchain
description
Toolchain management: declarative dependencies, automatic installs, install/exec/search/env commands, Aqua registry integration, version pinning, package verification
metadata.copyright
Copyright Cloud Posse, LLC 2026
metadata.version
1.0.0
metadata.category
dev-tooling
references
references/commands-reference.md

Atmos Toolchain

Purpose

The Atmos toolchain manages CLI tool installation and versioning natively, using the Aqua package registry ecosystem. It replaces external version managers (asdf, mise, aqua CLI) with a built-in system that integrates directly with atmos.yaml configuration.

Default Rule

Declare tool requirements where they are used, then run the owning Atmos command. Do not add atmos toolchain install before component, workflow, custom-command, or hook execution when the tool can be declared with dependencies.tools. Atmos installs missing declared tools and injects them into PATH for that execution context.

Use explicit atmos toolchain install only for shell bootstrap, cache warming, ad-hoc troubleshooting, or job-level tools that are not owned by a component, workflow, custom command, or hook.

Agents repeatedly get two things wrong here: putting an operation-specific tool version only in .tool-versions, and wrapping atmos itself in atmos toolchain exec. Both are covered below.

❌ Wrong — a component needs a pinned Terraform version, declared only in .tool-versions:

text
# .tool-versions
terraform 1.10.3

This is a repo-wide default. Nothing ties it to the vpc component, so a different component (or a different environment's .tool-versions) can silently drift the version this component actually needs.

✅ Right — pin it on the component that requires it:

yaml
components:
  terraform:
    vpc:
      dependencies:
        tools:
          terraform: "1.10.3"

.tool-versions still sets the repo-wide developer-shell default; dependencies.tools overrides it for this component's execution context, and travels with the component if it's vendored or reused elsewhere.

Core Concepts

.tool-versions File

The .tool-versions file (asdf-compatible format) declares which tools and versions a project needs:

text
terraform 1.9.8
opentofu 1.10.3
kubectl 1.28.0
helm 3.13.0
jq 1.7.1
  • One tool per line, format: toolname version [version2 version3...]
  • Multiple versions per tool are supported; first version is the default
  • File location: project root (default), overridable via toolchain.versions_file in atmos.yaml, --tool-versions, or ATMOS_TOOL_VERSIONS

Use .tool-versions for repo-wide developer shell defaults and general tools that every developer, agent, or interactive shell should see. Atmos can auto-install these defaults for custom commands and shell integration, but .tool-versions is not the preferred home for operation-specific requirements.

Use dependencies.tools when the tool is part of a stack/component/workflow/command contract. Those dependencies are installed and injected into that execution context and can override .tool-versions defaults. Do not rely on .tool-versions alone when CI or a stack requires a specific Terraform, OpenTofu, scanner, or generator version.

Where to Declare a Tool
NeedPreferred declaration
Component needs Terraform/OpenTofu, scanner, or generatorStack/component dependencies.tools
Workflow step needs a CLIWorkflow dependencies.tools
Custom command invokes a CLI such as bat, tree, jq, or checkovCommand dependencies.tools
Hook invokes a scanner or custom binaryComponent dependencies.tools for the hooked component
One-off local shell, manual verification, or cache warmatmos toolchain install plus atmos toolchain env
Tool Installation Path

By default, tools are installed in the XDG data directory for Atmos, such as ~/.local/share/atmos/toolchain on Linux/macOS. If the XDG data directory cannot be created, Atmos falls back to .tools in the current project.

Installed tools use this layout under the selected install path:

text
<install-path>/bin/{os}/{tool}/{version}/{binary}

Override the install path with toolchain.install_path in atmos.yaml or ATMOS_TOOLCHAIN_PATH when tools must be stored in a project-local, shared, or cached directory.

Registries

Atmos supports three registry types for discovering and downloading tools:

Aqua Registry -- The primary source, providing 1,000+ tools:

yaml
registries:
  - name: aqua
    type: aqua
    source: https://github.com/aquaproj/aqua-registry/tree/main/pkgs
    priority: 10

Inline (Atmos) Registry -- Define tools directly in atmos.yaml:

yaml
registries:
  - name: custom
    type: atmos
    priority: 150
    tools:
      owner/repo:
        type: github_release
        url: "asset_{{.Version}}_{{.OS}}_{{.Arch}}"
        format: tar.gz

File-Based Registry -- Local or remote Aqua-format files:

yaml
registries:
  - name: corporate
    type: aqua
    source: file://./custom-registry.yaml
    priority: 100

Priority System: Higher numbers are checked first. First match wins. Typical ordering: inline (150) > corporate (100) > public aqua (10).

Aliases

Map short names to fully qualified tool identifiers:

yaml
toolchain:
  aliases:
    terraform: hashicorp/terraform
    tf: hashicorp/terraform
    kubectl: kubernetes-sigs/kubectl
Package Verification

Atmos verifies downloaded packages before extraction when Aqua or inline registry metadata provides checksums, signatures, or attestations. Defaults are non-breaking: verify when metadata exists, allow packages without metadata.

yaml
toolchain:
  verification:
    checksums: when_available   # when_available | required | disabled
    signatures: when_available  # when_available | required | disabled
    verifier_install: auto      # auto | path_only

Supported methods: checksums (sha256, sha512, sha1, md5), cosign, slsa-verifier, GitHub artifact attestations via gh, and minisign.

Configuration in atmos.yaml

yaml
toolchain:
  install_path: .tools              # Optional override; default is XDG data dir
  versions_file: .tool-versions     # Path to version file

  aliases:
    terraform: hashicorp/terraform
    tf: hashicorp/terraform

  registries:
    # Inline tools (highest priority)
    - name: my-tools
      type: atmos
      priority: 150
      tools:
        jqlang/jq:
          type: github_release
          url: "jq-{{.OS}}-{{.Arch}}"

    # Aqua registry (fallback)
    - name: aqua
      type: aqua
      source: https://github.com/aquaproj/aqua-registry/tree/main/pkgs
      priority: 10

  verification:
    checksums: when_available
    signatures: when_available
    verifier_install: auto

Key Commands

See references/commands-reference.md for the full command/flag reference. Common commands:

bash
atmos toolchain install [tool@version]      # Bootstrap/cache warm, or ad-hoc install
atmos toolchain update [tool...]            # Update pinned tools to newest available version
atmos toolchain uninstall <tool@version>    # Remove installed tool
atmos toolchain add/remove/set/get <tool>   # Manage .tool-versions entries
atmos toolchain search/info/list/which      # Discovery and inspection
atmos toolchain exec <tool@version> -- ...  # Run a pinned third-party binary
atmos toolchain env/path                    # Shell PATH integration
atmos toolchain registry list/search        # Registry inspection
atmos toolchain du / clean                  # Disk usage / cleanup

Prefer dependencies.tools for normal Atmos execution. Component, workflow, custom-command, and hook runs install missing declared tools automatically.

Anti-pattern: never run atmos toolchain exec -- atmos .... Every atmos command is already toolchain-aware — it resolves and injects declared tool paths for its own execution automatically (see "Default Rule" above). Wrapping atmos in atmos toolchain exec is redundant at best and a sign the tool declaration is missing at worst. toolchain exec exists only to run a third-party binary (terraform, kubectl, a scanner CLI) directly, pinned to a specific managed version, outside of an atmos-orchestrated command — never to invoke atmos itself.

If a workflow/custom-command/hook step needs to confirm a tool is present on PATH without installing it, use the require step type (alias assert) instead of dependencies.tools (which auto-installs) or a hand-rolled command -v shell check — see atmos-workflows for the tools:/files:/ dirs: config.

Environment Variables

VariableDescription
ATMOS_GITHUB_TOKEN / GITHUB_TOKENGitHub token for higher API rate limits
ATMOS_TOOL_VERSIONSOverride .tool-versions file path
ATMOS_TOOLCHAIN_PATHOverride tool installation directory
ATMOS_TOOLCHAIN_ENV_FORMATDefault format for env command

Precedence Order

  1. CLI flags (highest)
  2. Environment variables
  3. atmos.yaml configuration
  4. XDG data directory
  5. .tools fallback
Show full SKILL.md (602 more words)Show less

Shell Integration

If you only ever run atmos <subcommand>, you do not need shell integration — Atmos resolves and injects declared tool paths for its own execution automatically. Shell integration is only for getting the raw tool binary directly into an interactive shell or a non-Atmos script (e.g. running terraform by hand outside of atmos terraform ...).

Add to ~/.bashrc or ~/.zshrc for automatic PATH setup:

bash
eval "$(atmos toolchain env --format=bash)"

Other shell formats: --format=fish, --format=powershell, --format=github (for CI).

For shells where evaluation is not desirable, prepend the generated toolchain path directly:

bash
export PATH="$(atmos toolchain path):$PATH"

Set ATMOS_TOOLCHAIN_PATH when the installed-tools directory must be shared, cached, or moved outside the repo checkout:

bash
export ATMOS_TOOLCHAIN_PATH="$HOME/.cache/atmos/tools"
eval "$(atmos toolchain env --format=bash)"

In GitHub Actions, use the GitHub format only when later job-level steps need direct shell access to toolchain binaries. When $GITHUB_PATH is available, Atmos appends toolchain paths to it automatically:

yaml
- name: Add toolchain paths for later job-level scripts
  run: atmos toolchain env --format=github

Tool Dependencies in Atmos Config

Declare tool dependencies close to the thing that needs them. Atmos installs missing tools from the toolchain registry and injects them into the command environment. Use these dependencies for tools required by stacks, components, workflows, and custom commands; use .tool-versions for general project tools.

yaml
# Top-level defaults
dependencies:
  tools:
    aws-cli: "^2.0.0"

# Component-type defaults
terraform:
  dependencies:
    tools:
      terraform: "~> 1.10.0"
      tflint: "^0.54.0"

# Component-specific tools
components:
  terraform:
    vpc:
      dependencies:
        tools:
          terraform: "1.10.3"
          checkov: "latest"

# Workflow tools
workflows:
  validate:
    dependencies:
      tools:
        tflint: "^0.54.0"

# Custom command tools
commands:
  - name: scan
    dependencies:
      tools:
        checkov: "3.0.0"

Use exact versions for reproducible CI, SemVer ranges for managed upgrade windows, and latest only for non-production workflows where drift is acceptable.

SemVer ranges only work here (and via atmos version track). The ~> 1.10.0 / ^2.0.0 style ranges above are resolved by the separate dependencies.tools subsystem at terraform/helmfile/packer exec time — they are not accepted by the atmos toolchain add/install/set CLI commands in "Key Commands" below (those take exact versions, latest, pr:, sha:, or ref: only; a range like atmos toolchain add terraform@"~>1.0" fails). They also don't work in .tool-versions, which is intentionally exact-version-only — it's an asdf-compatible format, and asdf itself has no range support (see asdf-vm/asdf#1392). If you're looking for "how do I pin a range," use dependencies.tools in stack YAML or atmos version track, not the toolchain CLI commands.

In Atmos CI, prefer dependencies.tools over GitHub setup actions such as hashicorp/setup-terraform or opentofu/setup-opentofu. Setup actions install a runner-level binary, while Atmos tool dependencies travel with the stack, component, workflow, or command that requires the tool and are injected into that execution context. If an agent is about to add atmos toolchain install <tool> to CI, first check whether the tool belongs on the component, workflow, or custom command that invokes it.

Custom Registries in atmos.yaml

Add your own tools under toolchain.registries when the public Aqua registry does not define them. Use a high-priority type: atmos registry for inline definitions, and keep the public Aqua registry as a fallback:

yaml
toolchain:
  aliases:
    policyctl: company/policyctl

  registries:
    - name: company
      type: atmos
      priority: 150
      tools:
        company/policyctl:
          type: github_release
          url: "policyctl_{{.Version}}_{{.OS}}_{{.Arch}}.tar.gz"
          format: tar.gz
          binary_name: policyctl

    - name: aqua
      type: aqua
      source: https://github.com/aquaproj/aqua-registry/tree/main/pkgs
      priority: 10

For shared registry files, use type: aqua with a local or remote source and a higher priority than the public registry:

yaml
toolchain:
  registries:
    - name: company-registry
      type: aqua
      source: file://./toolchain/company-registry.yaml
      priority: 100

Template Variables in Registries

Aqua and inline registries support Go templates in asset URLs:

VariableDescription
{{.Version}}Full version string
{{trimV .Version}}Version without 'v' prefix
{{.OS}}Operating system (linux, darwin, windows)
{{.Arch}}Architecture (amd64, arm64)

Common Patterns

Project Setup

Combine repo-wide defaults in .tool-versions with the toolchain.aliases/registries config shown under "Configuration in atmos.yaml" above:

text
# .tool-versions
hashicorp/terraform 1.9.8
kubernetes-sigs/kubectl 1.28.0
helmfile/helmfile 0.168.0

Tools declared on components, workflows, and commands are installed when those operations run. Use atmos toolchain list to inspect local installs; use atmos toolchain install only to pre-warm a developer shell or CI cache.

CI/CD Integration
yaml
# GitHub Actions: normal Atmos operation, no preinstall step needed
- run: atmos terraform plan vpc -s prod

# Optional: expose already-managed tool paths to later non-Atmos shell steps
- run: atmos toolchain env --format=github

See "Custom Registries in atmos.yaml" above for adding a company-internal tool registry.

Unsupported Aqua Features

These Aqua features are intentionally not supported to keep Atmos focused. Note that github_content and github_archive package types are supported (see atmos toolchain registry docs) — only the following are missing:

  • go_install, go_build_install, cargo package types (use github_release or http for pre-built binaries instead)
  • version_filter, version_expr version manipulation
  • import (use multiple registries instead)
  • command_aliases (use toolchain.aliases in atmos.yaml)

© 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

SKILL.md and 1 other file (references) in agent-skills/skills/atmos-toolchain of cloudposse/atmos.

  • SKILL.md
  • references/commands-reference.md

Open the folder on GitHubat commit 36726ae

Compare with similar skills

Atmos Toolchain 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 Toolchain compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Atmos Toolchain this skillcloudposse/atmos1.4k—~3.9kAutomated 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 Toolchain

What does Atmos Toolchain do?

Toolchain management: declarative dependencies, automatic installs, install/exec/search/env commands, Aqua registry integration, version pinning, package verification. Atmos Toolchain is an agent skill from cloudposse/atmos.

When should I use Atmos Toolchain?

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

How do I install Atmos Toolchain in Claude Code?

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

How do I install Atmos Toolchain in Codex?

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

Can I use Atmos Toolchain 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-toolchain -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-toolchain, .gemini/skills/atmos-toolchain, .github/skills/atmos-toolchain and .opencode/skills/atmos-toolchain in your project.

What does Atmos Toolchain need to run?

Going by SKILL.md and its folder, Atmos Toolchain needs credentials named ATMOS_GITHUB_TOKEN and GITHUB_TOKEN. Our summary lists: A credential in ATMOS_GITHUB_TOKEN; A credential in GITHUB_TOKEN.

Does Atmos Toolchain access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Atmos Toolchain 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 Toolchain use?

Atmos Toolchain 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 Toolchain use?

About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Atmos Toolchain?

Skills that share tags, products or a category with Atmos Toolchain: 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 Toolchain?

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.