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-aigit 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-ai)<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-ai"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-ai/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-ai"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 233 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 297 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 346 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- medium MCP Rug Pull · line 167 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 180 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 185 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 192 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00084 | $0.04323 |
| Opus 5.5 | $0.00034 | $0.01729 |
| Sonnet 5.5 | $0.00017 | $0.00865 |
| Haiku 4.5 | $0.00008 | $0.00432 |
Grade C, and why
atmos-ai scanned grade C with 2 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
For Codex CLI, append to `~/.codex/config.toml`: Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- The exported `.mcp.json` is safe to commit -- it contains no secrets (worst case: IAM role How it starts
The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atmos AI and MCP
Purpose
Use this skill when the work is about AI and Atmos together. There are two integration patterns:
- AI uses Atmos: external AI assistants use Atmos Agent Skills for knowledge and Atmos MCP
servers for tools. This includes
atmos mcp start,atmos mcp export, the Atmos MCP server, Atmos Pro MCP, AWS MCP servers, and MCP+skills setup for Claude Code, Codex, Gemini, Cursor, Windsurf, GitHub Copilot, and similar clients. - Atmos uses AI: Atmos calls AI providers directly or through local CLI providers. This
includes
atmos ai ask,atmos ai chat,atmos ai exec,--aicommand analysis, API providers, CLI providers, external MCP server routing, and CLI provider MCP pass-through.
This skill is the coordination layer for AI providers, agent skills, MCP configuration, MCP export, and the "AI inside AI" setup where an external assistant calls Atmos, and Atmos can also call AI.
Routing
| Work | Use |
|---|---|
AI provider setup, atmos ai, --ai, MCP server/client config, MCP export, agent-skill pairing |
Stay in atmos-ai |
| Project discovery, resolved stacks/components, provenance, query filters, affected analysis | Load atmos-introspection |
Terraform plan/apply/deploy/destroy, --affected, --all, --query, CI execution matrices |
Load atmos-terraform or atmos-ci |
| Cloud credentials, identities, SSO/OIDC, auth-wrapped MCP servers | Load atmos-auth |
Tool binaries for MCP servers, uvx/npx resolution, Aqua aliases, PATH injection |
Load atmos-toolchain |
Atmos Uses AI: Commands and Providers
atmos ai chat
atmos ai ask "What stacks do we have?"
atmos ai exec "validate stacks" --format json
atmos ai sessions list
atmos ai skill list
# Analyze any Atmos command output with AI
atmos terraform plan vpc -s prod --ai
atmos terraform plan vpc -s prod --ai --skill atmos-terraform
atmos terraform plan vpc -s prod --ai --skill atmos-terraform,atmos-stacks
Use API providers for CI/CD and non-interactive automation. Use CLI providers when the user wants to reuse an existing local subscription such as Claude Code, Codex CLI, or Gemini CLI.
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.
- 3d ago Changed · +28 lines e338a13da750
- 1mo ago Changed · +7 lines 150f9995be2b
- 1mo ago First seen · 361 lines · 84 tokens per session scan C 352237c562ce
atmos-ai is a skill published in the GitHub repository cloudposse/atmos (1,407 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 4,323 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
wikipedia
Search and read Wikipedia via x wkp — MediaWiki API, no API key, zero install; query, extract, suggest, and DDG route in one module. Load for wiki, wikipedia, encyclopedia lookup, article summary.
cve
Look up CVE records via x cve — cached, zero-API-key, daily xz TSV. Load for cve, vulnerability id, kev, epss, nvd, cvelist, or security advisory.
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…
api-less-website
api-less-website skill — placeholder, documentation to be added. Do not load as a real skill yet.
gke-basics
Trigger: Use when working with Google Kubernetes Engine basics — cluster setup, node pools, workloads, networking, and storage fundamentals.
huawei-cloud-apig-instance-management
Manage Huawei Cloud APIG (API Gateway, dedicated instances) via hcloud CLI: instance lifecycle (create/list/delete), API groups, API create/update/delete, publish/offline, request throttling policies, signature keys, access control (ACL) policies, and public ingress EIP binding, plus read-only diagnosis of public…