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
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cloudposse/atmos --skill atmos-toolchaingit clone --depth 1 https://github.com/cloudposse/atmosWrote 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-toolchain)<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-toolchain"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-toolchain/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-toolchain"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-toolchain.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 | $0.00033 | $0.03818 |
| Opus 5 | $0.00016 | $0.01909 |
| Sonnet 5 | $0.00007 | $0.00764 |
| Haiku 4.5 | $0.00003 | $0.00382 |
Grade A, and why
atmos-toolchain 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 9d 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 — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
# .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:
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:
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_filein atmos.yaml,--tool-versions, orATMOS_TOOL_VERSIONS
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.
- 9d ago First seen · 446 lines · 33 tokens per session scan A 1f78fef79e3d
atmos-toolchain is a skill published in the GitHub repository cloudposse/atmos (1,376 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 3,818 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
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform.
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.
beacon
Specialist agent for observability and reliability engineering. Covers SLO/SLI design, distributed tracing, alert strategies, dashboard design, capacity planning, toil automation, and reliability reviews.