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-introspectiongit 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-introspection)<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-introspection"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-introspection/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-introspection"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-introspection.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 | $0.00044 | $0.02972 |
| Opus 5.5 | $0.00018 | $0.01189 |
| Sonnet 5.5 | $0.00009 | $0.00594 |
| Haiku 4.5 | $0.00004 | $0.00297 |
Grade A, and why
atmos-introspection 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 today.
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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atmos Introspection
Purpose
Atmos provides powerful introspection commands (describe and list) for querying the stack graph,
component configurations, dependencies, and change impact. AI agents operating in a terminal should
use these commands to understand the user's workspace instead of guessing at configurations.
When to Use Introspection
- Before generating configuration -- Run
atmos describe componentto see the current resolved config - To find dependencies -- Run
atmos describe dependentsto see what depends on a component - To understand project structure -- Run
atmos list stacksandatmos list components - For CI/CD -- Run
atmos describe affectedoratmos list affectedto detect changed stacks - To debug configuration -- Use
--provenanceto trace where values originate
Describe Commands
atmos describe component
Display the complete, fully resolved configuration for a specific component in a stack.
atmos describe component vpc -s plat-ue2-prod
atmos describe component vpc -s plat-ue2-prod --format json
atmos describe component vpc -s plat-ue2-prod --provenance
atmos describe component vpc -s plat-ue2-prod -q '.vars.cidr_block'
Key flags:
-s, --stack(required) -- Stack name-f, --format-- Output format (yaml, json). Default: yaml--provenance-- Show where each configuration value originated (file:line:column)-q, --query-- Filter output with yq expressions--process-templates/--process-functions-- Enable/disable template and YAML function processing--skip-- Skip specific YAML functions during processing
The output includes all resolved sections: vars, settings, env, backend, metadata,
deps, inheritance, and remote_state_backend.
atmos describe stacks
Show fully deep-merged configuration for all stacks and their components.
atmos describe stacks
atmos describe stacks -s plat-ue2-prod
atmos describe stacks --components vpc,eks
atmos describe stacks --component-types terraform
atmos describe stacks --sections vars,settings
atmos describe stacks -q '.[] | select(.vars.environment == "prod")'
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.
- today Changed · +25 lines · +7 tokens per session a96046c34225
- 1mo ago Changed · -1 lines 6a53e4b3d831
- 1mo ago Changed · +3 lines f2172aec88da
- 1mo ago First seen · 334 lines · 37 tokens per session scan A b0c338d1aab4
atmos-introspection is a skill published in the GitHub repository cloudposse/atmos (1,406 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 2,972 once invoked, about $0.0002 per session on Opus 5.5. 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
clum-mcp
A procedure for using clum, a remote Linux operations platform that runs commands through a secure proxy rather than direct SSH. It also describes how to inspect systems, investigate failures, compare solutions, and review incidents.
claw-admin
Claw system administration: service management, IM connections, logs, cron, and workspace diagnostics. Use when the user asks to manage claw services, connect/disconnect IM platforms, view logs, or perform system-wide operations.
optimize
Review code for efficiency and performance. Triggered by "/optimize" when user wants to identify bottlenecks or improve performance.
gke-basics
Trigger: Use when working with Google Kubernetes Engine basics — cluster setup, node pools, workloads, networking, and storage fundamentals.
huaweicloud-troubleshooting
Troubleshoot Huawei Cloud CLI, API, SDK, deployment, permission, region, quota, endpoint, and resource errors. Use when commands fail, APIs return errors, resources are missing, or the user needs a structured diagnosis.
doris-debug-cloud
Use for Doris storage-compute separation (cloud mode) issues: meta-service latency, cache miss storms, object store throughput, and shared-nothing config conflicts in compute groups.