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 agentmods add skills/voidmatcha/ui-clone-skills/ui-capturenpx skills add voidmatcha/ui-clone-skills --skill ui-capturegit clone --depth 1 https://github.com/voidmatcha/ui-clone-skillsWrote 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/voidmatcha/ui-clone-skills/ui-capture)<a href="https://agentmods.dev/skills/voidmatcha/ui-clone-skills/ui-capture"><img src="https://agentmods.dev/badge/skills/voidmatcha/ui-clone-skills/ui-capture.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.04552 |
| Opus 5 | $0.00026 | $0.02276 |
| Sonnet 5 | $0.00010 | $0.00910 |
| Haiku 4.5 | $0.00005 | $0.00455 |
Grade A, and why
ui-capture scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
printf 'Missing system deps:%s\n\nFastest fix:\n tmp=$(mktemp) && curl -LsSf -o "$tmp" https://raw.githubusercontent.com/voidmatcha/ui-clone-skills/main/install.sh && bash "$tmp" && rm -f "$tmp"\n\nOr install manually:\n How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ui-capture - Visual Capture & Reference
Capture reference screenshots and transition videos, detect transition types, and optionally capture matching implementation clips as downstream verification evidence.
Primary trigger: Capture/reference evidence from a URL.
Non-goals: Do not use ui-capture as the primary mismatch diagnosis tool; hand failing validation evidence to visual-debug.
Session rule
Always use --session <project-name> with every agent-browser command.
Token rule
Pipe large eval output to a file, then Read only what you need:
agent-browser --session <s> eval "<script>" > tmp/ref/<name>.json
Never let large JSON print to stdout — it wastes tokens.
eval JSON unwrap rule
agent-browser eval returns the script's return value JSON-encoded, so a
script that returns JSON.stringify(obj) writes a double-quoted JSON
string to disk (e.g. "{\"sections\":[...]}"), not the object itself.
Passing that file straight to jq '.sections' fails with jq: Cannot index string with string "sections".
Unwrap once before further jq work:
agent-browser --session <s> eval "(() => JSON.stringify({...}))()" > raw.json
jq -r 'fromjson' raw.json > data.json # now a real object; pipe to jq freely
Or skip the inner JSON.stringify entirely — agent-browser eval already
serializes the return value, so returning the plain object works too and
avoids the unwrap step:
agent-browser --session <s> eval "(() => ({sections: [...]}))()" > data.json
When to use
- Standalone: invoke
ui-capture <reference-url> [local-url] [component](Claude slash command:/ui-capture ...) - From ui-reverse-engineering: Phase A (reference), Phase 4 (verification) —
<component>MUST be passed so output lands intmp/ref/<component>/where the pipeline gates look - From orchestration workflows: when SPEC.md has
reference_url
Output directory:
<component>provided →tmp/ref/<component>/(matchesui_clone.gateexpectations — flat, nocapture/parent)<component>omitted →tmp/ref/capture/(standalone usage; not gated)
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.
- today Changed · +35 lines · +24 tokens per session b87a24f8b0ad
- 5d ago First seen · 306 lines · 27 tokens per session scan A 6d0a4154aa73
ui-capture is a skill published in the GitHub repository voidmatcha/ui-clone-skills (9 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 4,552 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-mobile-app
Use when the user wants to start a new Power Apps mobile app (Expo / React Native / TypeScript, targeting iOS and Android) from scratch.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
genpage
Creates, updates, and deploys Power Apps generative pages for model-driven apps using React v17, TypeScript, and Fluent UI V9. Orchestrates specialist agents for planning, entity creation, and code generation. Use it when user asks to build, retrieve, or update a page in an existing Microsoft Power Apps model-driven…
create-code-app
Creates Power Apps code apps using React and Vite. Use when building code apps, scaffolding projects, or deploying to Power Platform.
motherduck-create-dive
Create, edit, manage, share, or embed MotherDuck Dives — live React + SQL dashboards, charts, and data apps saved in the workspace. Use for any dashboard, chart, KPI display, or data visualization over MotherDuck data, and for Dive authoring mechanics such as getdiveguide, useSQLQuery, local preview, version history…
migrate-radix-to-base
Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects.