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.
Borrowing it
Nothing to install: this file belongs to cloudposse/atmos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cloudposse/atmos/main/.claude/skills/field-test/SKILL.mdgit 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/field-test)<a href="https://agentmods.dev/skills/cloudposse/atmos/field-test"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/field-test/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/field-test"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/field-test.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 | $0.00116 | $0.05215 |
| Opus 5.5 | $0.00046 | $0.02086 |
| Sonnet 5.5 | $0.00023 | $0.01043 |
| Haiku 4.5 | $0.00012 | $0.00522 |
Grade A, and why
field-test 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 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.
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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Field Test
Hands-on, adversarial test pass of $ARGUMENTS (the feature/command named when this skill
was invoked, e.g. atmos vendor pull).
If no target was given, default to the change introduced on the current branch rather than
asking. Resolve the actual pull-request base branch when one is available
(gh pr view --json baseRefName -q .baseRefName for the current branch), falling back to the
repository's default branch (gh repo view --json defaultBranchRef -q .defaultBranchRef.name)
when no PR exists yet. Do NOT use the upstream tracking branch (@{u}) as the base — for a normal
feature branch that tracks origin/<same-branch-name>, diffing against its own upstream produces
an empty or near-empty diff, not the PR's actual changes, once the branch has been pushed.
A branch NAME from gh (e.g. develop) is not guaranteed to be a usable git ref in THIS checkout
— shallow clones, detached HEADs, and worktrees with a narrow fetch refspec can have the name
without the commits. Before running any diff, verify the base actually resolves here
(git rev-parse --verify --quiet <candidate>^{commit}), trying in order: origin/<resolved-name>,
<resolved-name> — take the first that verifies. Do not fall back to origin/main/main when
resolved-name came from an actual PR base other than the default branch (e.g. a PR targeting
develop) — diffing against main instead of the PR's real base compares against the wrong
history and can silently miss real changes or include unrelated ones. origin/main/main are
legitimate fallback candidates only in the no-PR case (gh pr view returned nothing, so
resolved-name already IS the repository's default branch) or when gh itself isn't available at
all. If a known, non-default PR base doesn't resolve as either origin/<resolved-name> or
<resolved-name>, stop and ask the user which base to diff against — do not run `git diff
Goal: catch "vibe-coded slop" — behavior that looks fine in code review but breaks or misleads a real user — not to re-run what automated tests already cover. Anticipate plausible user misunderstandings, not just obvious bugs.
This pass is investigation only. Do not fix anything you find — see Phase 5. Report and stop;
the user decides what to fix. Any follow-up fix work — including a plan to fix the findings, not
just the implementation — must close with the fix-log skill, not this one.
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 · +39 lines 85895debe53d
- 1mo ago First seen · 249 lines · 116 tokens per session scan A 17d300cccf14
field-test is a skill published in the GitHub repository cloudposse/atmos (1,405 stars, last pushed today), licensed Apache-2.0. It adds 116 tokens to every session and 5,215 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
lovable
Lovable MCP tool usage — deploy projects, message agent, test with agent-browser. Minimize credits by delegating to local repo.
agent-browser
Browser automation via Chrome/Chromium CDP — open, snapshot, click, screenshot. For testing web apps, mobile layouts, and automated interactions without Playwright/Puppeteer.
gke-basics
Trigger: Use when working with Google Kubernetes Engine basics — cluster setup, node pools, workloads, networking, and storage fundamentals.
aiox-qa
Activate Quinn (qa) for Test Architect & Quality Advisor. Use for comprehensive test architecture review, quality gate decisions, and code improvement. Provides thorough analysis including requirements traceability, risk assessment, and...
architect-first
Guide for implementing the Architect-First development philosophy - perfect architecture, pragmatic execution, quality guaranteed by tests. Use this skill when starting new features, refactoring systems, or when architectural decisions are needed. Enforces non-negotiables like complete design/documentation before…
review-story
QA gate for a story — verdict PASS/CONCERNS/FAIL/WAIVED + lifecycle transition. Use when: review story, qa gate, qa-gate, /review-story.