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 jeltehomminga/figma-design-skills --skill figma-design-extractgit clone --depth 1 https://github.com/jeltehomminga/figma-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/jeltehomminga/figma-design-skills/figma-design-extract)<a href="https://agentmods.dev/skills/jeltehomminga/figma-design-skills/figma-design-extract"><img src="https://agentmods.dev/badge/skills/jeltehomminga/figma-design-skills/figma-design-extract/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/jeltehomminga/figma-design-skills/figma-design-extract"><img src="https://agentmods.dev/badge/skills/jeltehomminga/figma-design-skills/figma-design-extract.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 | $0.00094 | $0.02385 |
| Opus 5 | $0.00047 | $0.01192 |
| Sonnet 5 | $0.00019 | $0.00477 |
| Haiku 4.5 | $0.00009 | $0.00238 |
Grade A, and why
figma-design-extract 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 12d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Design Extract — get the real design out of Figma
Read a Figma node into a design-spec table of exact values mapped to your codebase, before writing any component code. The table is both your build contract and the input to the companion design-fidelity-verify skill, which proves the running app matches it.
This skill is the design→code direction (read Figma, produce a spec). It is not a code→Figma generator — that's Figma's own figma-generate-design skill.
Why this exists (the failure mode it fixes)
Screenshot-as-truth. A model reads a Figma screenshot as "button, top-right" but cannot see that the radius is 8 not 12, the weight is 500 not 600, or the gap is 12 not 8. A screenshot is a visual reference only. Exact values come from Figma's structured data — variables and metadata — not from pixels. The bar is fidelity to the design's decisions — the right token — not literal pixel coordinates. Skip this and the design drifts the moment you start typing.
When to use
Trigger phrases: "implement this Figma screen/component", "build this design", "extract the Figma values", "get the tokens/spacing/colors from Figma", "match the Figma", or a figma.com/design/...node-id=... URL shared to build from.
Scope: any frontend repo (web or mobile). Backend/API repos have no UI to build.
Prerequisite: the Figma MCP server (Dev Mode MCP) connected, so get_variable_defs, get_metadata, get_design_context, and get_screenshot are available.
The extraction workflow
0. Resolve the node (don't trust stale IDs)
Get the node from the URL the designer shared, or from your issue tracker / design handoff. The node id is the node-id=NNNN-MMMM part of a Figma URL (the - becomes : in API calls, e.g. 1234:5678).
- Node ids go stale between handoff and build. Try the given id with
get_design_contextfirst; if it returns "node not found", search by a stable numeric prefix rather than the frame name (names get renamed and double-spaced). - Dark mode often lives on a mirror page with identical frame names — look on the sibling page, don't search globally.
- Keep every call node-scoped.
get_metadataon a 40-frame section blows the token budget. Always pass the specific node id.
What ships with it
5 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.
- 12d ago First seen · 118 lines · 94 tokens per session scan A 0508fa1240b4
figma-design-extract is a skill published in the GitHub repository jeltehomminga/figma-design-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 2,385 once invoked, about $0.0005 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
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
system-pitch
Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…
token-audit
Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…
ai-component-description
Generate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write…
context-engine-builder
Generate a context engine — seven structured blueprint files (UX, UI, content, accessibility, ethical, technical, business intelligence) that encode everything an AI agent needs to work with a design system. This produces YAML infrastructure in .ai/context-engine/, NOT a health score or quality assessment. Trigger…
stakeholder-brief
Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…