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.
npx skills add MadAppGang/magus --skill go-tuigit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/go-tui)<a href="https://agentmods.dev/skills/madappgang/magus/go-tui"><img src="https://agentmods.dev/badge/skills/madappgang/magus/go-tui/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/madappgang/magus/go-tui"><img src="https://agentmods.dev/badge/skills/madappgang/magus/go-tui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.02865 |
| Opus 5 | $0.00026 | $0.01432 |
| Sonnet 5 | $0.00010 | $0.00573 |
| Haiku 4.5 | $0.00005 | $0.00286 |
Grade A, and why
go-tui 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go TUI
Build Go terminal UIs that look like gonzo, btop, lazygit, and posting — colorful,
dense, graph-and-badge-heavy — not like cat output. The Charm stack (Bubble Tea +
Lip Gloss + Bubbles) is the foundation; ntcharts adds real charts; a verified screenshot
workflow lets you see your UI in color and fix what's wrong.
Two things make a TUI good, and this skill is organized around both:
- Sound architecture — clean Elm-style state/update/view, correct sizing, the right component for each job.
- A strong visual look — semantic color, data shown as shapes (bars/sparklines/ heatmaps), status as colored badges, dense panels over prose.
You cannot judge the second from source code. So the core loop is: build → screenshot in color → look → fix.
The aesthetic this skill is for (the through-line)
When the user wants a TUI, they almost always want it to look good and modern — and the bar this skill aims for is more colour, more graphs, less text. The failure mode to design against is not ugliness; it's under-baking — rendering a plain number or a flat one-color bar when the same five lines could render a smooth gradient meter or a sparkline. Reach for the rich representation by default; the plain one is the draft you didn't finish.
The default-visual contract. Don't decide case-by-case whether to visualize — map the data type to its visual and follow it:
| You have… | Default to… | Not… |
|---|---|---|
| a bounded value (%, ratio, 0–100) | a gradient meter (Blend1D, green→red across the fill) |
a bare number, or a flat single-color bar |
| a time series / recent history | a sparkline (braille ⣀⣤⣶⣿ or ▁▂▃▄▅▆▇█) |
a single latest number |
| a category distribution | a bar chart or stacked bar, colored per category | a list of "name: count" lines |
| counts over time × category | a heatmap row per category, brightness = magnitude | a table of numbers |
| a discrete status/level/method | a colored badge (dark ink on saturated bg) | plain colored text alone |
| genuine free narrative (logs, detail) | text — and only inside a log/detail panel | text as the main surface |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 1.6 KB
- references/bubbletea-architecture.md 4.7 KB
- references/color-and-aesthetics.md 10 KB
- references/components-and-charts.md 6.9 KB
- references/layout-patterns.md 3.8 KB
- references/lipgloss-styling.md 5.9 KB
- references/reference-apps.md 4.9 KB
- references/screenshot-workflow.md 6.4 KB
- references/testing.md 3.5 KB
- scripts/ansi-to-png.ts 4.2 KB runs code
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 · +6 lines 46a5d632eb33
- 6d ago First seen · 177 lines · 52 tokens per session scan A 71b90c23c00f
go-tui is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 2,865 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
gentleman-bubbletea
Bubbletea TUI patterns for Gentleman.Dots installer. Trigger: When editing Go files in installer/internal/tui/, working on TUI screens, or adding new UI features.
building-glamorous-tuis
Build terminal UIs with Charmbracelet (Bubble Tea, Lip Gloss, Gum). Use when: Go TUI, shell prompts/spinners, "make CLI prettier", adaptive layouts, async rendering, focus state machines, sparklines, heatmaps, kanban boards, SSH apps.
wings-component
Write a WINGS component (custom element in Go→WASM) — module file trio, wings.Register, the PranaMod lifecycle (InitData/Render), template binding syntax ({{expr}}, ?cond, arr/arr, &attr, @event), and parent-child events. Use when creating or editing a WINGS module, template, custom element, PranaMod, or any template…
templui
Apply templUI patterns when building Go/Templ web applications.
wings-build
Set up, build, and serve a WINGS app — Go module setup, the WASM build (GOOS=js), copying the JS runtime helpers, a static dev server, and the cross-platform cmd/build orchestrator (targets + the camelCase binding lint + rebuild-on-save dev mode). Use when scaffolding a new WINGS project, configuring its build, wiring…
templ
Write and review templ templates: syntax, components, attributes, styling, JavaScript data passing, escaping and sanitization, code generation, and testing.