atmos-git

atmos-git is a skill for Claude Code from cloudposse/atmos. It costs 64 tokens per session (1,458 once invoked), scanned A, original, Apache-2.0.

A set of Atmos features for managing Git repositories and GitOps workflows. GitOps means using version-controlled files to manage deployments and infrastructure changes.

In plain words
What is it for?
Use it to clone, initialize, update, inspect, compare, commit, push, and clean configured repositories, including repositories used for deployments.
Why use it?
It brings repository operations, authentication, signing, and managed working directories into one configuration-driven workflow. This reduces scattered scripts and manual repository handling.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the atmos plugin — 55 skills shipped together

Good fit Use it to clone, initialize, update, inspect, compare, commit, push, and clean configured repositories, including repositories used for deployments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cloudposse/atmos/atmos-git
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 · 1,407 stars · on GitHub · atmos.tools

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.

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

Made for: Claude Code.

Or install atmos, the plugin that ships this one along with the rest of its 55 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-git

README.md
[![agentmods](https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-git/github.svg)](https://agentmods.dev/skills/cloudposse/atmos/atmos-git)
Your own site
<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-git"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-git/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.

agentmods 80×15 button for atmos-git

Your own site · 80×15
<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-git"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-git.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,458 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 Tool Misuse · line 85
    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.
How audits are shown
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 5.1 $0.00064 $0.01458
Opus 5.5 $0.00026 $0.00583
Sonnet 5.5 $0.00013 $0.00292
Haiku 4.5 $0.00006 $0.00146

Measured 7d ago against content hash a716fa238ade, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

atmos-git 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 7d 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.

agent-skills/skills/atmos-git/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atmos Git

Use this skill for native Git repository management, GitOps automation, managed workdirs, local Git hook shims, signed commits, and GitHub auth through Atmos Auth or Atmos Pro STS.

Need Load
Atmos Pro GitHub App commits atmos-pro
github/sts credentials for private repos atmos-auth
Lifecycle git hooks atmos-hooks
Modernizing old GitHub Actions GitOps patterns atmos-modernization

Configuration

Configure managed repositories in atmos.yaml:

git:
  repositories:
    deployment:
      uri: https://github.com/acme/deployment.git
      branch: main
      auth:
        identity: atmos-pro
      commit:
        author:
          name: Atmos Bot
          email: [email protected]
        signing: auto               # auto | always | never

Use identities or github/sts for private GitHub access. Do not put tokens in repository URIs.

Commands

Command Purpose
atmos git list List configured repositories
atmos git clone <name-or-uri> Clone or reconcile a managed repository
atmos git init <name-or-path> Initialize a managed repository
atmos git pull <name-or-path> Fast-forward pull
atmos git status <name-or-path> Show working tree status
atmos git diff <name-or-path> Show changes
atmos git commit <name-or-path> --message "msg" Stage managed paths and commit
atmos git push <name-or-path> Push commits
atmos git clean <name> Remove managed workdirs

Use atmos git hooks install, run, and uninstall for local Git hook shims in the current repository. Shims pin the absolute atmos path at install time and fall back to PATH. The atmos git hooks run command exits with the failing step's code (fail() exits 1, errors.build().with_exit_code(5) exits 5).

Git Hook Environment

Read the full file on GitHub · 113 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. 7d ago Changed · +24 lines · +10 tokens per session a716fa238ade
  2. 1mo ago Changed · -1 lines 47590ff5e9e2
  3. 1mo ago First seen · 90 lines · 54 tokens per session scan A c298f9c71b96

Subscribe to this mod's changes

atmos-git is a skill published in the GitHub repository cloudposse/atmos (1,407 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 1,458 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 2026-09-03.