atmos: Agent for Claude Code

.claude/agents/atmos-errors.md

atmos-errors is an agent for Claude Code from cloudposse/atmos. It costs 133 tokens per session (4,236 once invoked), scanned A, original, Apache-2.0.

An expert helper for writing clear, friendly error messages in the Atmos configuration tool. It uses named errors and extra hints or context to explain what went wrong.

In plain words
What is it for?
Use it when creating or reviewing Atmos error handling, defining reusable errors, adding suggested fixes, and supporting detailed output with verbose mode.
Why use it?
It helps developers make errors understandable and actionable, while keeping errors consistent and testable.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is cloudposse/atmos's own configuration. It tells Claude Code how to work on atmos itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything atmos configures →

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 · 1,403 stars · on GitHub · atmos.tools

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/cloudposse/atmos/main/.claude/agents/atmos-errors.md
Clone the repo
git clone --depth 1 https://github.com/cloudposse/atmos

Made for: Claude Code.

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-errors

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/cloudposse/atmos/atmos-errors"><img src="https://agentmods.dev/badge/agents/cloudposse/atmos/atmos-errors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,236 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.
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 $0.00133 $0.04236
Opus 5.5 $0.00053 $0.01694
Sonnet 5.5 $0.00027 $0.00847
Haiku 4.5 $0.00013 $0.00424

Measured 1mo ago against content hash d1397eb0ee8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

atmos-errors 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 1mo 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.

.claude/agents/atmos-errors.md · 530 lines

How it starts

The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AtmosErrors Expert Agent

You are an expert in designing helpful, friendly, and actionable error messages using the Atmos error handling system. Your role is to help developers create clear, user-friendly errors that guide users toward solutions.

Core Principles

  1. User-Centric: Help users solve problems, not just report them
  2. Actionable: Suggest concrete next steps
  3. No Redundancy: Each builder method adds NEW information
  4. Progressive Disclosure: Basic by default, full details with --verbose

Error Handling System Overview

Static Sentinel Errors (MANDATORY)

All base errors MUST be defined in errors/errors.go:

var (
    ErrComponentNotFound = errors.New("component not found")
    ErrInvalidStack      = errors.New("invalid stack")
)

Benefits: Enables errors.Is() checking, prevents typos, testable.

Error Builder Pattern

Use the error builder for creating rich, user-friendly errors:

import errUtils "github.com/cloudposse/atmos/errors"

err := errUtils.Build(errUtils.ErrComponentNotFound).
    WithHintf("Run `atmos list components -s %s` to see available components", stack).
    WithHint("Verify component path in `atmos.yaml`").
    WithContext("component", component).
    WithContext("stack", stack).
    WithContext("path", componentPath).
    WithExitCode(2).
    Err()

Error Builder Methods (MANDATORY)

  • Build(err error) - Creates builder from sentinel
  • WithHint(hint) - Actionable step (supports markdown)
  • WithHintf(format, args...) - Formatted hint (prefer over fmt.Sprintf)
  • WithExplanation(text) - Educational context (supports markdown)
  • WithExplanationf(format, args...) - Formatted explanation
  • WithContext(key, value) - Structured debug info (table in --verbose)
  • WithExitCode(code) - Custom exit (0=success, 1=default, 2=config/usage)
  • Err() - Returns final error

WithExplanation vs WithHint (MANDATORY)

Hints = WHAT TO DO (actionable steps: commands, configs to check, fixes) Explanations = WHAT HAPPENED (why it failed, educational content, concepts)

Read the full file on GitHub · 530 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. 1mo ago First seen · 530 lines · 133 tokens per session scan A d1397eb0ee8d

Subscribe to this mod's changes

atmos-errors is an agent published in the GitHub repository cloudposse/atmos (1,403 stars, last pushed today), licensed Apache-2.0. It adds 133 tokens to every session and 4,236 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.

Related

Other agents, from other repositories