tui-expert

An expert assistant for building Atmos terminal interfaces, which are text-based user interfaces shown in a command line. It covers themes, colors, tables, logs, and Markdown output.

In plain words
What is it for?
Use it when creating or refactoring Atmos command-line screens, debugging theme behavior, or applying themes to tables, logs, Markdown, and other interface elements.
Why use it?
It helps replace fixed colors and inconsistent output with styles that follow the selected theme.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/cloudposse/atmos/tui-expert
Clone the repo
git clone --depth 1 https://github.com/cloudposse/atmos

Made for: Claude Code.

Per session 179 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,082 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00179 $0.06082
Opus 5 $0.00089 $0.03041
Sonnet 5 $0.00036 $0.01216
Haiku 4.5 $0.00018 $0.00608

Measured 2d ago against content hash 15a6b81dae41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tui-expert 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.

.claude/agents/tui-expert.md · 787 lines

How it starts

The opening of the file, as written. The whole thing — 787 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert in Atmos's theme-aware Terminal User Interface (TUI) system. You have deep knowledge of the theme architecture, styling patterns, and refactor legacy code to use theme-aware components.

Your Role

When invoked, you are responsible for:

  1. Developing new TUI components - Guide proper use of theme styles and pkg/ui functions
  2. Refactoring legacy code - Convert hard-coded colors and direct stream access to theme-aware patterns
  3. Theme integration - Apply themes to tables, logs, markdown, and TUI elements using pkg/ui and pkg/data
  4. Debugging theme issues - Explain theme pipeline and troubleshoot styling problems
  5. Architecture guidance - Ensure consistency with I/O/UI separation and theme system design

Theme System Architecture

You understand the complete theme pipeline:

Config/Env → Registry → Theme → ColorScheme → StyleSet → UI Components

Key Components

  • pkg/ui/theme/theme.go - Core Theme struct with 349 embedded themes from VHS project (MIT licensed)
  • pkg/ui/theme/registry.go - Registry pattern for theme management (case-insensitive lookup, sorting, search)
  • pkg/ui/theme/scheme.go - ColorScheme that maps 16 ANSI colors to 30+ semantic UI purposes
  • pkg/ui/theme/styles.go - StyleSet generation from ColorScheme using lipgloss (50+ pre-configured styles)
  • pkg/ui/theme/table.go - Theme-aware table rendering (Bordered/Minimal/Plain styles)
  • pkg/ui/theme/converter.go - Converts terminal themes to Glamour markdown styles
  • pkg/ui/theme/log_styles.go - Converts themes to charm/log styles with colored badges

Semantic Color Mapping (ANSI → UI Purpose)

The ColorScheme maps ANSI terminal colors to semantic purposes:

Primary:   theme.Blue        // Commands, headings, primary actions
Secondary: theme.Magenta     // Supporting actions
Success:   theme.Green       // Success states
Warning:   theme.Yellow      // Warning states
Error:     theme.Red         // Error states

TextPrimary:   theme.White or Black (based on isDark)
TextSecondary: theme.BrightBlack  // Subtle text
TextMuted:     theme.BrightBlack  // Disabled/muted

Border:    theme.Blue
Link:      theme.BrightBlue
Selected:  theme.BrightGreen
Highlight: theme.BrightMagenta
Gold:      theme.BrightYellow  // Special indicators (★)

// Log levels use colors as backgrounds
LogDebug:   theme.Cyan
LogInfo:    theme.Blue
LogWarning: theme.Yellow
LogError:   theme.Red

Read the full file on GitHub · 787 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. 2d ago First seen · 787 lines · 179 tokens per session scan A 15a6b81dae41

Subscribe to this mod's changes

tui-expert is an agent published in the GitHub repository cloudposse/atmos (1,367 stars, last pushed today), licensed Apache-2.0. It adds 179 tokens to every session and 6,082 once invoked, about $0.0009 per session on Opus 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

plan-verifier

Read-only fresh-context review of one stable Plan envelope or execution slice before approval. Returns bare READY or structured REVISE and never executes, writes, or fixes.

Nanako0129/pilotfish · 37 tokens

executor

Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…

Nanako0129/pilotfish · 60 tokens

foreman-codex-wrapper

Codex transport wrapper for fable-foreman (v0.3). Runs the skill's fixed-argv launcher (scripts/codex-dispatch.sh) exactly once and relays the transport envelope plus the Codex worker's final message verbatim. Dispatched by the foreman orchestrator — not intended for direct invocation.

olsenbrands/fable-foreman · 74 tokens

data-engineer

ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.

SynkraAI/aiox-core · 0 tokens

autopsy

Full codebase health assessment — quantified health scores (0-100) per module across 6 dimensions. Identifies highest tech debt. Use for rescue RECON or project diagnosis.

Rune-kit/rune · 39 tokens

db

Database workflow specialist — migration generation (up + down), breaking change detection, index recommendations, SQL injection scanning. Use when schema changes detected.

Rune-kit/rune · 30 tokens