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 memi-design/design-skills --skill figma-web-capturegit clone --depth 1 https://github.com/memi-design/design-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/memi-design/design-skills/figma-web-capture)<a href="https://agentmods.dev/skills/memi-design/design-skills/figma-web-capture"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/figma-web-capture/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/memi-design/design-skills/figma-web-capture"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/figma-web-capture.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 | $0.00033 | $0.00744 |
| Opus 5 | $0.00016 | $0.00372 |
| Sonnet 5 | $0.00007 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
figma-web-capture 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 11d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Web Capture
Use this when a user wants to bring a webpage into Figma as editable layers instead of a screenshot.
This is a practical workflow built on Figma's public html-to-design
capture asset. Treat it as an unofficial bookmarklet path, not as a guaranteed
product surface. Re-check the script URL if Figma changes the flow.
What It Does
- Loads Figma's public
capture.jshelper into the current page. - Serializes the rendered DOM into Figma layers.
- Copies the capture to the clipboard so it can be pasted into any open Figma file.
- Supports capturing the full viewport or a selected element.
Public Script
The capture helper lives at:
https://mcp.figma.com/mcp/html-to-design/capture.js
Load that script into the page, then use the capture toolbar to copy the result to the clipboard.
As of March 27, 2026, this public URL returns HTTP 200.
Recommended Workflow
- Open the target page in a desktop browser.
- Wait for fonts, images, and lazy-loaded content to finish rendering.
- Scroll to the exact section you want to capture.
- Run the bookmarklet or injected script that loads
capture.js. - In the toolbar, choose
Copy to clipboard. - Switch to Figma and paste into a dedicated scratch frame or page.
- If you only need part of the page, use
Select elementbefore copying.
Safe Positioning
- Capture the smallest stable container that still includes the content you need.
- Paste into a scratch frame first, then move pieces into the final canvas.
- Keep one capture per page or frame so imported layers stay organized.
- Capture after scrolling into the intended viewport, not before.
Example Bookmarklet
javascript:(function(){var s=document.createElement('script');s.src='https://mcp.figma.com/mcp/html-to-design/capture.js';document.head.appendChild(s);setTimeout(function(){window.location.hash='figmacapture&figmadelay=1000';var s2=document.createElement('script');s2.src='https://mcp.figma.com/mcp/html-to-design/capture.js';document.head.appendChild(s2);},500);})();
What ships with it
1 file 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.
- 11d ago First seen · 77 lines · 33 tokens per session scan A 8caeb02497c0
figma-web-capture is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 744 once invoked, about $0.0002 per session on Opus 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
separateweb-capture
Capture a URL into a full-page screenshot, cropped UI item PNGs, and a JSON manifest. Use when the user says separateweb capture , asks to capture a website, or wants UI extraction assets without running the SeparateWeb web app.
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
motion-lexicon
Design, build, compose, implement, review, and contribute polished product interfaces with Motion Lexicon components and motion primitives. Use this skill when a user asks for a complete React page, landing page, dashboard, settings screen, or product surface in the Motion Lexicon visual language; asks what motion…
motion-craft
Use when an interface moves and the movement has to feel right — durations and easing, what must never animate, fixing motion that reads sluggish, cheap or janky, and reduced-motion. Web and native. NOT the visual system (that is design), NOT the graded critique (that is design-loop).
accessibility-compliance-accessibility-audit-v2
Accessibility Audit and Testing workflow skill. Use this skill when the user needs You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance and the operator should preserve the upstream…
a11y-audit
Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…