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 agentmods add skills/cloudposse/atmos/atmos-hooksnpx skills add cloudposse/atmos --skill atmos-hooksgit 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-hooks)<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-hooks"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-hooks.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00046 | $0.01989 |
| Opus 5 | $0.00023 | $0.00994 |
| Sonnet 5 | $0.00009 | $0.00398 |
| Haiku 4.5 | $0.00005 | $0.00199 |
Grade A, and why
atmos-hooks 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atmos Hooks
Use this skill for lifecycle hooks that run before or after component operations, or for generation hooks declared in a scaffold template.
Hooks can run scanners, policy checks, store writes, Git actions, custom commands, or other toolchain-aware automation around Terraform, Helm, Kubernetes, and other component commands.
Related Skills
| Need | Load |
|---|---|
| Store output hooks | atmos-stores |
Shared step fields and kind: step payloads |
atmos-steps |
| Git hooks and GitOps repositories | atmos-git |
| Tool installation for hook commands | atmos-toolchain |
| CI summaries and Atmos Pro upload | atmos-ci and atmos-pro |
Hook Shape
Hooks are configured in stack manifests at global, component-type, or component scope.
hooks:
store-vpc-outputs:
events:
- after.terraform.apply
kind: store
name: prod/ssm
outputs:
vpc_id: .vpc_id
components:
terraform:
vpc:
hooks:
scan-plan:
events:
- after.terraform.plan
kind: trivy
Modern dotted event names such as after.terraform.plan are preferred. Legacy hyphenated event
names may appear in older stacks; modernize them when editing nearby config.
Lifecycle Events
Use before/after events for component operations, for example:
before.terraform.init,after.terraform.initbefore.terraform.plan,after.terraform.planbefore.terraform.apply,after.terraform.applybefore.terraform.deploy,after.terraform.deploybefore.terraform.test,after.terraform.testbefore.terraform.output,after.terraform.output— fires foratmos terraform output, useful for backfilling a store from already-deployed infrastructure without anapplybefore.terraform.refresh,after.terraform.refresh
Kubernetes provides before/after events for render, diff/plan, apply/deploy,
delete, and validate. Native Helm provides template, diff, apply/deploy, and
delete; Helmfile provides template, diff, apply/sync/deploy, and destroy.
Use the canonical dotted events and remember that command aliases normalize to their execution
event (deploy to apply, Kubernetes plan to diff, and Helmfile sync to apply).
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.
- yesterday First seen · 192 lines · 46 tokens per session scan A 3045de89a581
atmos-hooks is a skill published in the GitHub repository cloudposse/atmos (1,372 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 1,989 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
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
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.
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…
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…
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.
ops-cost-optimization
Audits SaaS/PaaS, cloud commitment, and AI/LLM costs across Vercel, Supabase, AWS, and Cloudflare. Use when analyzing bills, right-sizing plans, or buying commitments.