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 KaiUweHella/figma-bridge-mcp --skill figma-bridge-code-to-figmagit clone --depth 1 https://github.com/KaiUweHella/figma-bridge-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/kaiuwehella/figma-bridge-mcp/figma-bridge-code-to-figma)<a href="https://agentmods.dev/skills/kaiuwehella/figma-bridge-mcp/figma-bridge-code-to-figma"><img src="https://agentmods.dev/badge/skills/kaiuwehella/figma-bridge-mcp/figma-bridge-code-to-figma/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/kaiuwehella/figma-bridge-mcp/figma-bridge-code-to-figma"><img src="https://agentmods.dev/badge/skills/kaiuwehella/figma-bridge-mcp/figma-bridge-code-to-figma.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 | $0.00126 | $0.01918 |
| Opus 5 | $0.00063 | $0.00959 |
| Sonnet 5 | $0.00025 | $0.00384 |
| Haiku 4.5 | $0.00013 | $0.00192 |
Grade A, and why
figma-bridge-code-to-figma 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 6d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Figma from Code
Treat the rendered application as the visual contract, the source repository as the semantic contract, and the existing Figma file as the design-system contract. Preserve all three instead of drawing a flattened approximation.
Pin the Figma Bridge transport
- Use the tools from the server bundled with this skill: namespace
figma-bridge, server idfigma-bridge-mcp. Do not select a similarly named Figma MCP by name alone. - Start with this server's
figma_status. Its result and every later result must identify_mcp: "figma-bridge-mcp". - A failed probe proves only that Figma Bridge transport is unavailable. It does not prove that Figma or another Figma MCP is unavailable.
- Do not silently switch to another Figma MCP for a write. Name the unavailable transport and ask the user before changing tools or write semantics.
Choose the source path
- Inspect the source route, component tree, styles, tokens, assets, fonts, interactive states, viewport, and current working-tree changes.
- For an existing browser-rendered UI, use the Bridge DOM-capture workflow:
render --print-browser-capture, capture at the reference viewport, thenrender --dom-capture ... --verify. Do not manually translate the same UI into simplified JSX. Acceptance evidence must identify thedom-captureadapter; hand-authored JSX cannot substitute for that provenance. - Use hand-authored Bridge JSX only for new views or components that do not yet have a renderable DOM source.
- Call
figma_referencewithname: "workflow:code-to-figma"once and follow the returned version-specific command sequence.
Reconcile before writing
- If
figma-bridge.jsonor a Design Entity exists, start withlink context. Stop on a code/Figma conflict and present both sides; never pick a winner. - Inspect the target Figma page, component inventory, variables, styles, linked entities, and existing screens before creating anything.
- Build a compact reuse map from each source component to one of: exact linked Figma component, compatible existing component, or new local component. Design Entity and Storybook links outrank names; names alone never authorize replacement.
- Resolve only genuine ambiguities with the user. Proceed when the source and existing design system identify one clear answer.
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.
- 6d ago Changed · +7 lines 342b3fafba92
- 11d ago First seen · 137 lines · 126 tokens per session scan A 810c8b29add5
figma-bridge-code-to-figma is a skill published in the GitHub repository KaiUweHella/figma-bridge-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 126 tokens to every session and 1,918 once invoked, about $0.0006 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.