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 TN0123/one-shot-ui --skill skillgit clone --depth 1 https://github.com/TN0123/one-shot-uiWrote 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/tn0123/one-shot-ui/skill)<a href="https://agentmods.dev/skills/tn0123/one-shot-ui/skill"><img src="https://agentmods.dev/badge/skills/tn0123/one-shot-ui/skill/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/tn0123/one-shot-ui/skill"><img src="https://agentmods.dev/badge/skills/tn0123/one-shot-ui/skill.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 | $0.00028 | $0.02702 |
| Opus 5.5 | $0.00011 | $0.01081 |
| Sonnet 5.5 | $0.00006 | $0.00540 |
| Haiku 4.5 | $0.00003 | $0.00270 |
Grade A, and why
one-shot-ui 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 2mo 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have access to the one-shot-ui CLI tool. Use it to analyze reference
screenshots and compare your implementations against them.
When to Use
- The user provides a screenshot or mockup and asks you to build it
- The user wants to compare their implementation against a design
- The user wants to iteratively refine a UI to match a reference
- The user wants a different UI that copies the style/aesthetic of a screenshot (same design language, different content) — see "Style transfer" below
Workflow
Step 1: Extract the design
Run one-shot-ui extract <reference.png> --json --overlay to get:
- Layout nodes with positions, sizes, colors, gradients, shadows, border radii
- Text blocks with content, font size, weight, color, and
monospace - Design tokens (spacing scale, color palette, radius scale)
- Component clusters (repeated visual patterns)
- Implementation plan (suggested CSS strategy: grid/flex/absolute)
Pass --dpr for Retina/Mac screenshots. A 2x screenshot reports every pixel at
double its CSS value (a 35px heading measures 70px), which throws off fonts, spacing
and sizing. If you know the screenshot is from a Retina/Mac display, pass --dpr 2 so
sizes and bounds come back in CSS pixels. Otherwise check the report's scale block:
units: "css-px" means values are normalized; a scale.scaleHint means it might be
Retina and you should re-run with --dpr 2. Build to the reported CSS pixels.
Step 2: Build the UI
Use the extracted data to write the implementation directly. Set exact:
- Colors (hex values from extraction)
- Spacing (px values from spacing measurements)
- Typography (font sizes, weights from text blocks)
- Border radii, shadows, gradients (from style extraction)
Build to the rulers block — this is the single biggest lever for sizing/spacing.
extract reports deterministic pixel-projection "rulers" so you don't have to eyeball or
hand-measure geometry:
rulers.bands— background-zone heights down the page (e.g. a top header/nav bar's exact height in CSS px, with its background hex). Set those container heights/paddings exactly.rulers.columns— content column left edges and widths (sidebar width, main column, card columns). Drive your container widths / grid tracks from these.rulers.gutters— the exact gaps between columns. Use them forcolumn-gap, margins, padding. These are CSS px (DPR already applied). Matching them up front avoids the slow "off by ~16px, shifted right" iteration loop.
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.
- 2mo ago First seen · 195 lines · 28 tokens per session scan A 82650590cecb
one-shot-ui is a skill published in the GitHub repository TN0123/one-shot-ui (6 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 2,702 once invoked, about $0.0001 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 2026-08-31.
one-shot-ui compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| one-shot-uiTN0123/one-shot-ui | Skill | 6 | 3mo ago | MIT | A | 28 | Claude Code, Codex |
| desktop-brand-builderQwenLM/qwen-code | Skill | 29k | today | Apache-2.0 | A | 68 | Claude Code, Codex |
| datavizQwenLM/qwen-code | Skill | 29k | today | Apache-2.0 | A | 26 | Claude Code |
| frontend-designHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 21 | Claude Code, Codex |
| write-zot-themespatriceckhart/zot | Skill | 359 | yesterday | MIT | A | 23 | Claude Code, Codex |
| anycap-human-interactionanycap-ai/anycap | Skill | 50 | 17d ago | MIT | A | 190 | Claude Code |
| design-skillOverbrilliant/ob-1 | Skill | 29 | 11d ago | Apache-2.0 | A | 82 | Claude Code, Codex |