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/pull-request/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/pull-request)<a href="https://agentmods.dev/skills/cloudposse/atmos/pull-request"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/pull-request/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/pull-request"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/pull-request.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Tool Misuse · line 122 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Prompt Injection · line 23 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Agent Snooping · line 83 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 220 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 219 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00060 | $0.03776 |
| Opus 5.5 | $0.00024 | $0.01510 |
| Sonnet 5.5 | $0.00012 | $0.00755 |
| Haiku 4.5 | $0.00006 | $0.00378 |
Grade A, and why
pull-request 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 2d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request Preparation (Atmos)
Use this skill every time you open or update a PR. It encodes three policies that the Atmos repo enforces via CI and that the team has been burned by repeatedly:
- Every PR needs exactly one semver label. Unlabeled PRs fail the
PR Semver LabelsCI check. minorandmajorPRs require a blog post AND a roadmap update. TheCheck for changelog and roadmap updatesworkflow gates merging on both.featured[]in the roadmap is curated. Never auto-promote a shipped milestone intofeatured[]— only the user decides.
If you violate any of these, CI fails and the PR can't merge. Follow this skill across both phases: complete the pre-push checklist before git push, then immediately work through the post-push / PR checklist (open the PR, apply the label, monitor CI).
The label decision tree
The Atmos repo has four mutually exclusive release labels (plus other category labels that don't affect release docs):
| Label | When | CI requires blog + roadmap? |
|---|---|---|
no-release |
Internal refactor, new internal helper, dependency bump with zero user-visible behavior, docs fixes | No |
patch |
Bug fix, performance fix, error-message improvement, small UX polish — user-visible but not a feature | No |
minor |
New user-visible feature, new flag, new command, new config option, default flip that users see | YES |
major |
Breaking change: removed/renamed flag, schema migration, CLI behavior reversal | YES |
How to choose
Ask, in order:
- Would a user upgrading Atmos see ANY visible change? Behavior, output, errors, performance, new flags, new commands, removed flags, changed defaults? If no, use
no-release. This is the most common case for foundation/plumbing PRs. - Is this a breaking change? Removed flags, renamed flags, changed semantics, schema bumps that require user action? Use
major. Document the migration in the blog post. - Is this net-new functionality? New command, new flag, new config option that users will adopt? Use
minor. Write a blog post. - Anything else user-visible (bug fix, UX polish, error-message rewrite, output formatting): use
patch. No blog post required.
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.
- 2d ago Changed · +31 lines 8e40abc08be4
- 1mo ago Changed · +1 lines ef3ab98ec344
- 1mo ago Changed 30f7800fa014
- 1mo ago First seen · 222 lines · 60 tokens per session scan A 8f2e3ced5133
pull-request is a skill published in the GitHub repository cloudposse/atmos (1,403 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 3,776 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 2026-08-30.
Other skills, from other repositories
csv
CSV data processing — view, filter, convert, merge tabular data. Zero barrier — use with x-cmd, Python, or awk. Use for "csv", "data", "table", "spreadsheet", "conversion".
git
Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".
work
Handle issue/PR work items with worktree isolation. Triggered by "/work [issuelink|description]" to start focused work.
gke-basics
Trigger: Use when working with Google Kubernetes Engine basics — cluster setup, node pools, workloads, networking, and storage fundamentals.
repo
Convention + tooling for where agent-cloned repos live and how their worktrees are arranged. Default bare repo at /.x-repo/.bare/ / / .git with linked working trees under /.x-repo/ / / [/@ ]. Discovered via x repo ls. Worktree management via x repo wt. Use for "where to clone", "git clone path", "workspace layout"…
gh
You have access to gh (GitHub CLI) for repository and project management.