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 makifbaysal/tasktrooper --skill screen-mockup-htmlgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/screen-mockup-html)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/screen-mockup-html"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/screen-mockup-html/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/makifbaysal/tasktrooper/screen-mockup-html"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/screen-mockup-html.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 | $0.00063 | $0.04174 |
| Opus 5.5 | $0.00025 | $0.01670 |
| Sonnet 5.5 | $0.00013 | $0.00835 |
| Haiku 4.5 | $0.00006 | $0.00417 |
Grade A, and why
screen-mockup-html 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 4d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screen Mockup HTML
Overview
The HTML documents on the task ARE the design — one per variant, titled design: <screen> · <letter> (design: Invoices — list · A), so the review page can lay them side by side for the human to choose one. A human reviews each in a sandboxed frame, selects passages and comments on them; developers receive them in their run context as plain text. Nothing in them runs, loads or reacts — so every state is drawn, side by side, as its own static frame, and every decision a reviewer may question is text they can select.
Core principle: Draw states, don't simulate them. Lay each frame out by its own class, not by media queries — the review pane is not the device. It is a pan-and-zoom canvas, like Figma: frames sit at their real widths in rows as wide as they need, and the reviewer drags and pinches to move around them — so never put frames in a scrolling box.
Document anatomy
Keep these ids stable across revisions; review comments and the hand-off cite them.
One document per variant; each holds that variant only, complete.
header#top—<h1>the screen and the variant (Invoices — list · A — table first); one meta line: task key, design system version (base and layer), date, content language.section#notes— purpose in one sentence; this variant's idea, whom it serves, what it costs, and whether it is the one you recommend (design-variants); the decisions on palette, type and layout and why (avoid-ai-default-looks); tokens or components this design proposes to add; draft copy; any state that does not apply, with the reason; the self-check result.section#structure— the ASCII wireframes of this variant at 375 and the wide width in<pre>. They survive the text rendition developers get; the pixels do not.section#variant-a(#variant-bin the· Bdocument, …) —<h2>Variant A — <the idea></h2>, one line on the trade-off, then a strip with the 375 and the wide default frames.section#states-a(…) — the states grid: every state at 375, and at the wide frame the default plus each state whose layout differs there (every-state-designed). Dark theme frames sit in the same grid.section#controls— each control the screen uses in default, hover, focus-visible, active, disabled and loading, side by side.
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.
- 4d ago First seen · 184 lines · 63 tokens per session scan A 9a4427141d11
screen-mockup-html is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 4,174 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 2026-10-09.
Other skills, from other repositories
web-prototype
General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed assets/template.html and pasting section layouts from references/layouts.md. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.
design-critique
Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.
web-prototype-taste-brutalist
Swiss industrial-print web prototype. Newsprint canvas, monolithic black grotesque, viewport-bleeding numerals, hairline grid dividers, hazard-red accent, ASCII syntax decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Swiss Industrial Print mode).
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
mockuplm
Create visual UX mockups using HTML/CSS files (.mockup.html). Use when the user wants to design UI, wireframes, visual layouts, or plan features visually.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.