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 agentlas-ai/agentlas-desktop --skill url-to-codegit clone --depth 1 https://github.com/agentlas-ai/agentlas-desktopWrote 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/agentlas-ai/agentlas-desktop/url-to-code)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/url-to-code"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/url-to-code/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/agentlas-ai/agentlas-desktop/url-to-code"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/url-to-code.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 | $0.00032 | $0.00428 |
| Opus 5.5 | $0.00013 | $0.00171 |
| Sonnet 5.5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
url-to-code 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.
What it actually says
Skill Purpose
Faithfully captures and reproduces the visual appearance, styling tokens, asset hierarchy, and interactions of a live URL into a local runnable frontend prototype.
Preconditions
- The user must supply a target URL and confirm permission to recreate the site.
- Browser automation tools (
@agentlas-browseror@playwright) must be available. - If the user requests a redesign or new style for a URL, redirect to
$get-context→$ideate.
Steps
- Full-Page & Multi-Viewport Capture:
- Navigate to the source URL and perform top-to-bottom captures across desktop and mobile viewports.
- Extract DOM structure, typography, color palettes, spacing metrics, and responsive breakpoints.
- Harvest Assets & Interactions:
- Download or map image assets, logos, fonts, and icons into the local project bundle (avoid hotlinking external assets).
- Test and document states for menus, modals, dropdowns, tabs, and interactive controls.
- Construct Prototype Codebase:
- Write clean, modular frontend code faithfully replicating the captured design.
- Local Runtime & Visual QA (
$design-qa):- Start the local preview server and capture rendered screenshots.
- Run side-by-side comparison against the original site captures to eliminate visual regressions.
- Handoff: Verify
design-qa.mdreportsfinal result: passed, keep the local server running, and present the prototype.
Outputs
- Complete standalone local prototype codebase replicating the source website.
- Localized asset files and project
design-qa.mdverification report.
Verification
- Validate visual correspondence between the live URL capture and the local prototype rendering.
- Confirm zero reliance on external hotlinked assets.
- Verify that
design-qa.mdconcludes withfinal result: passed.
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 First seen · 36 lines · 32 tokens per session scan A a48a77034d48
url-to-code is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 428 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.
Other skills, from other repositories
architecture-diagram
How to draw and maintain the architecture diagram Ensemblr keeps for a workspace — ensemblrgetarchitecturediagram to fetch the stored one (it answers with null when nobody has drawn this workspace yet), the IR shape, how to derive it from the codebase, and ensemblrupdatearchitecturediagram to store it. Read this when…
frame-macos-notification
Realistic macOS notification banner with app icon, title, and body, suited to video overlays or product teasers.
winui-design
Read before writing or changing WinUI 3 XAML: choosing controls, pages and navigation, layout, Fluent Design, theming, accessibility, x:Bind, real samples, and checking that APIs exist with winapp find-api. Not for WPF or WinForms UI, even if the app uses the Windows App SDK.
figma-generate-design
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the…
openscreen-design
Use this skill to generate well-branded interfaces and assets for OpenScreen (an AI-native screen-recording studio & video editor), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
vellum-avatar
Customize the assistant's avatar - build a native character, upload an image, or generate one with AI.