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 TrungLee003/figma-agent-mcp --skill create-screengit clone --depth 1 https://github.com/TrungLee003/figma-agent-mcpWrote 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/trunglee003/figma-agent-mcp/create-screen)<a href="https://agentmods.dev/skills/trunglee003/figma-agent-mcp/create-screen"><img src="https://agentmods.dev/badge/skills/trunglee003/figma-agent-mcp/create-screen.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 5.1 | $0.00018 | $0.00275 |
| Opus 5 | $0.00009 | $0.00138 |
| Sonnet 5 | $0.00004 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
create-screen 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 7d 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
Create Screen Skill
Overview
14-step deterministic procedure to create high-fidelity UI screens in native Figma.
Steps
- Inspect canvas & design system: Discover existing components and variables.
- Plan component hierarchy: Outline frame layout and child hierarchy.
- Resolve component matches: Match buttons, cards, inputs from local library.
- Resolve design tokens: Match colors, spacing, radius to Figma Variables.
- Construct root frame: Create container with Auto Layout.
- Construct regions: Add header, hero, content, footer sections.
- Instantiate components: Create instances and bind instance properties.
- Populate content: Add text nodes with safe font loading.
- Configure Auto Layout: Set padding, spacing, and sizing (HUG/FILL).
- Bind variables: Attach semantic tokens to fills and strokes.
- Execute batch: Send batched commands to bridge.
- Re-read structure: Query created nodes.
- Validate: Check zero sizes, clipped text, alignment.
- Repair loop: Fix issues if detected (max 3 bounded attempts).
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.
- 7d ago First seen · 28 lines · 18 tokens per session scan A b08bc355b13d
create-screen is a skill published in the GitHub repository TrungLee003/figma-agent-mcp (1 stars, last pushed 19d ago), licensed MIT. It adds 18 tokens to every session and 275 once invoked, about $0.0001 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.