atmos-profiles

atmos-profiles is a skill for Claude Code, Codex from cloudposse/atmos. It costs 35 tokens per session (591 once invoked), scanned A, original, Apache-2.0.

A guide to Atmos profiles, which are named configuration overlays selected for a developer, CI job, tenant, cloud account, or environment. A profile changes selected settings while keeping the shared base configuration.

In plain words
What is it for?
Use it to define profile directories, activate profiles from the command line or environment, and override authentication, toolchain, and other configuration per context.
Why use it?
It makes it possible to switch contexts without editing the main project configuration or maintaining separate copies of it.

Skill for Claude CodeCodex

Part of the atmos plugin — 51 skills shipped together

About the project

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.

cloudposse/atmos · 1,372 stars · on GitHub

Install

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.

agentmods
npx agentmods add skills/cloudposse/atmos/atmos-profiles
Any agent
npx skills add cloudposse/atmos --skill atmos-profiles
Clone the repo
git clone --depth 1 https://github.com/cloudposse/atmos

Made for: Claude Code, Codex.

Or install atmos, the plugin that ships this one along with the rest of its 51 skills.

Wrote 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.

agentmods badge for atmos-profiles

README.md
[![agentmods](https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-profiles.svg)](https://agentmods.dev/skills/cloudposse/atmos/atmos-profiles)
Your own site
<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-profiles"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-profiles.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 591 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00591
Opus 5 $0.00017 $0.00296
Sonnet 5 $0.00007 $0.00118
Haiku 4.5 $0.00003 $0.00059

Measured yesterday against content hash 6ed5e2237fd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atmos-profiles 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 yesterday.

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.

agent-skills/skills/atmos-profiles/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atmos Profiles

Use this skill when configuring or troubleshooting Atmos profiles: named configuration overlays selected with --profile or ATMOS_PROFILE.

Purpose

Profiles let teams switch configuration contexts without changing the base project config. Use them for developer, CI, tenant, cloud account, or environment-specific overrides.

atmos --profile developer terraform plan vpc -s dev
ATMOS_PROFILE=ci atmos terraform deploy vpc -s prod

Use --profile with no value in an interactive terminal to open a multi-select picker of every discovered profile. Non-interactive contexts (CI, scripts) must pass --profile=<name> or ATMOS_PROFILE explicitly.

Profile Layout

Keep profile files focused and aligned with the sections they override:

profiles/
  developer/
    atmos.yaml
    auth.yaml
  ci/
    atmos.yaml
    auth.yaml

Profile configuration is merged into the active Atmos configuration. Put shared defaults in the base config, then keep each profile to the smallest override needed.

Profile Config

Configure the profile search location in root config when the default location is not sufficient:

profiles:
  base_path: profiles

Example profiles/ci/auth.yaml override:

auth:
  providers:
    github-oidc:
      kind: github/oidc
      region: us-east-1
  identities:
    deploy:
      kind: aws/assume-role
      via:
        provider: github-oidc

Routing

Need Load
Profile activation, directory layout, merge behavior stay in atmos-profiles
Auth providers, identities, OIDC, SSO, keyring in profiles atmos-auth
CI use of ATMOS_PROFILE atmos-ci
Tool versions or registries that differ by profile atmos-toolchain
Base paths and profile-relative file layout atmos-project-layout

Guardrails

  • Keep profile overrides small and predictable; avoid duplicating the whole base atmos.yaml.
  • Use the same provider and identity names across profiles when callers should not care which profile is active.
  • Prefer ATMOS_PROFILE in CI and --profile for one-off local commands.
  • Verify the active merged configuration with atmos describe config or the relevant atmos describe component command.

Read the full file on GitHub · 88 lines

Changes

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.

  1. yesterday First seen · 88 lines · 35 tokens per session scan A 6ed5e2237fd0

Subscribe to this mod's changes

atmos-profiles is a skill published in the GitHub repository cloudposse/atmos (1,372 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 591 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.

Related

Other skills, from other repositories

github-release-management

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.

ruvnet/RuView · 27 tokens

skypilot-multi-cloud-orchestration

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

davila7/claude-code-templates · 51 tokens

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…

triggerdotdev/trigger.dev · 68 tokens

hunt-cicd

Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pullrequesttarget Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log…

uphiago/recon-skills · 118 tokens

devops-cloud

DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.

travisjneuman/.claude · 38 tokens

cicd-secrets-exfil

Extracting CI secrets / OIDC tokens once you have code execution in a build job — echo/printenv exfil, log-masking bypass (base64, char-split, reversal), OIDC token abuse to assume cloud roles, GITHUBTOKEN / CIJOBTOKEN scope abuse, cache / artifact secret leakage, provenance pivot.

PurpleAILAB/Decepticon · 75 tokens