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/changelog/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/changelog)<a href="https://agentmods.dev/skills/cloudposse/atmos/changelog"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/changelog/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/changelog"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Prompt Injection · line 39 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00065 | $0.02779 |
| Opus 5.5 | $0.00026 | $0.01112 |
| Sonnet 5.5 | $0.00013 | $0.00556 |
| Haiku 4.5 | $0.00006 | $0.00278 |
Grade A, and why
changelog 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changelog (Blog Post) Authoring
Use this skill whenever you create or edit a post under website/blog/. It is the single source of truth
for the template, tags, authors, and style rules — CLAUDE.md, the pull-request skill, and the docs
skill all point here instead of restating these rules. Don't re-duplicate them elsewhere.
When a post is required
Only non-draft PRs targeting main, labeled minor or major, need one — see the pull-request skill's
label decision tree. CI enforces this via .github/workflows/changelog-check.yml, which checks for a new
website/blog/*.md or *.mdx file (draft PRs, and PRs targeting a branch other than main, are exempt
entirely). Write posts as .mdx regardless — Rule 3 below embeds <CastEmbed> as real JSX, which only
.mdx renders; CI accepts .md but that's not this repo's convention.
If a change is genuinely internal-only with zero user-visible effect, it doesn't get a post at all — that
invariant belongs to the roadmap skill ("no changelog post for internal-only refactors"); don't work around
it by writing an implementation-heavy post instead.
File and frontmatter
Create website/blog/YYYY-MM-DD-<slug>.mdx:
---
slug: descriptive-slug
title: "Clear Title"
authors: [username]
tags: [feature]
---
Open on the PAIN the reader already feels — the broken/tedious/confusing thing they live with
today — then name the change as the relief.
<!--truncate-->
## The Problem
...
## The Fix
...
## How to Use It
...
## Get Involved
.mdx, YAML frontmatter,<!--truncate-->immediately after the intro paragraph(s) — that's what shows in the blog feed.- Never open the body with
## What Changed— lead with the problem (see Rule 1).
Tags — read website/blog/tags.yml, never invent one
User-facing: feature, enhancement, bugfix, dx, breaking-change, security, documentation,
deprecation, experimental, atmos-pro. Internal/contributor-only, zero user impact: core.
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 · +9 lines dd1cadf99d21
- 1mo ago Changed 3fe389ff7465
- 1mo ago Changed · +4 lines 90e727de53ae
- 1mo ago Changed · +10 lines ab1a6bee81c3
- 1mo ago Changed · +24 lines a2328fb6f62f
- 1mo ago First seen · 146 lines · 65 tokens per session scan A 84f3e7f4681c
changelog is a skill published in the GitHub repository cloudposse/atmos (1,405 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 2,779 once invoked, about $0.0003 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".
ontology-database
Typed knowledge graph via TSV append-only log — entity CRUD, directed relations, schema validation, multi-hop reasoning. CLI via x ondb, protocol readable by AWK/Python/JS/SQLite.
meme
Generate meme images by overlaying text onto templates. Zero barrier — works with Python + Pillow, no framework needed. Templates are fetched on demand from the awesome-meme data repo. Use for "meme", "meme generator", "text overlay", "distracted boyfriend", "image macro".
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".
tsv
TSV data processing — view, filter, convert tab-separated data. Zero barrier — use with x-cmd, awk, or Python. Use for "tsv", "tab-separated", "data", "conversion".
qr
QR code generation — terminal display, PNG output, pure shell encoding. Zero barrier — use with x-cmd, Python qrcode, or any QR library. Use for "qr", "qrcode", "barcode", "encode".