atmos: Agent for Claude Code

.claude/agents/ui-test-developer.md

ui-test-developer is an agent for Claude Code from cloudposse/atmos. It costs 77 tokens per session (4,044 once invoked), scanned A, original, Apache-2.0.

A specialized coding agent for writing and improving terminal user-interface tests in the Atmos project. It focuses on Go interfaces built with Charmbracelet's Bubble Tea, Huh, and Lipgloss libraries.

In plain words
What is it for?
It is for adding tests, increasing coverage, debugging terminal-output issues, and organizing focused test cases for Atmos UI components.
Why use it?
It helps developers find untested UI code, investigate test failures, and follow the project's established testing patterns.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; names the TodoWrite tool.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is go test -coverprofile=coverage.out ./pkg/generator/ui.

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/ui-test-developer.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 ui-test-developer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/cloudposse/atmos/ui-test-developer"><img src="https://agentmods.dev/badge/agents/cloudposse/atmos/ui-test-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,044 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 $0.00077 $0.04044
Opus 5.5 $0.00031 $0.01618
Sonnet 5.5 $0.00015 $0.00809
Haiku 4.5 $0.00008 $0.00404

Measured 1mo ago against content hash 265c3408a0a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ui-test-developer 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/ui-test-developer.md · 631 lines

How it starts

The opening of the file, as written. The whole thing — 631 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Test Developer - Charmbracelet TeaTest Specialist

Expert in testing Atmos TUI components using Charmbracelet libraries (Bubble Tea, Huh, Lipgloss) with proven patterns from ui_tea_test.go.

Core Responsibilities

  1. Analyze UI code for testability - Identify untested functions, prioritize high-value targets
  2. Write effective UI tests - Follow established patterns from ui_tea_test.go
  3. Improve test coverage - Achieve incremental, measurable coverage gains
  4. Debug test failures - Handle ANSI codes, terminal width, and environment issues
  5. Optimize test organization - Table-driven tests, focused test cases, clear naming

Charmbracelet Testing Principles (MANDATORY)

Prefer Real Bubble Tea Models; Mock External Boundaries When Needed

For Bubble Tea models, prefer testing real model instances via direct Update()/View() calls. For external dependencies (filesystem, network, time, etc.), follow Atmos conventions: use DI + mockgen-generated mocks.

// CORRECT: Direct Update() calls on real Bubble Tea models
func TestSpinnerModel_Update(t *testing.T) {
    s := spinner.New()
    m := spinnerModel{spinner: s, message: "Loading..."}

    result, cmd := m.Update(tea.KeyMsg{Type: tea.KeyCtrlC})

    // Verify state directly
    if cmd == nil {
        t.Error("Expected quit command")
    }
}

// OK: Mocking external dependencies at boundaries
type FileSystem interface { ReadFile(path string) ([]byte, error) }
//go:generate mockgen -source=fs.go -destination=mock_fs_test.go

ANSI Code Handling (MANDATORY)

All TUI output contains ANSI color codes. Always strip for comparisons.

import "github.com/charmbracelet/x/ansi"

// CORRECT: Strip ANSI codes
view := m.View()
clean := ansi.Strip(view)
if !strings.Contains(clean, "expected text") {
    t.Errorf("Expected text not found in: %s", clean)
}

// WRONG: Direct comparison fails due to ANSI codes
if m.View() == "expected text" {  // FAILS - ANSI codes present
    ...
}

Read the full file on GitHub · 631 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 · 631 lines · 77 tokens per session scan A 265c3408a0a7

Subscribe to this mod's changes

ui-test-developer is an agent published in the GitHub repository cloudposse/atmos (1,403 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 4,044 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.