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 fledgeling-co/fledgeling-plugins --skill tui-designgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/tui-design)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/tui-design"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/tui-design/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/fledgeling-co/fledgeling-plugins/tui-design"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/tui-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00238 | $0.04129 |
| Opus 5.5 | $0.00095 | $0.01652 |
| Sonnet 5.5 | $0.00048 | $0.00826 |
| Haiku 4.5 | $0.00024 | $0.00413 |
Grade A, and why
tui-design 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.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tui-design
You cannot capture a screen that does not exist yet, and that is the whole
problem this skill has that tui-craft:tui-craft does not. Its instrument reads a running
program. Before there is one, the only artifact is a proposal, and the usual way
of writing that proposal is a terminal layout drawn by hand in a fenced code
block.
That drawing is almost always wrong, for a mechanical reason rather than a
careless one. Drawing it means counting characters, and characters are not cells.
len("🚀 Deploy") is 8 and it occupies 9. One wide glyph puts every column after
it off by one, the border does not close, and the mock looks perfectly fine in
the message that produced it, because nothing in that message measured anything.
The same arithmetic fails the same way on CJK labels, on box-drawing runs, and on
any string a combining mark passes through.
So the mock stops being a drawing. You declare what the screen contains and how it divides, a compiler does every piece of cell arithmetic, and what comes out is a real frame in tui-craft's schema that its gates read directly.
Using Gemini? Read gemini.md for this skill's task-specific calibration and artifact checks. Its older runs do not establish Gemini 3.8 capability limits: preserve the user's selected implementation lane, and apply a model-specific route only when the current model or an observed failure supports it.
The line between this skill and tui-craft
The split is author versus instrument, not "does a program exist yet". Both skills work on the same frame type and the distinction is what a frame may be used to claim:
- A composed frame (
kind: "mock") supports claims about the design: what it occupies at this size, whether its roles form a ladder, whether its selection survives losing colour, whether its columns fit their content. - It supports no claim about a running program. Not that the app draws this, not that a bug is fixed, not that a screen is ready. Those need a capture, and tui-craft owns them.
What ships with it
8 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.
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.
- 1mo ago Changed 20ec8ebf6b9a
- 1mo ago First seen · 300 lines · 238 tokens per session scan A 91f19cb0dc8e
tui-design is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 238 tokens to every session and 4,129 once invoked, about $0.0010 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 2026-09-04.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.