Borrowing it
Nothing to install: this file belongs to GeekyAnts/geeklego. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GeekyAnts/geeklego/geeklego-v2-beta/.claude/skills/figma-sync/SKILL.mdgit clone --depth 1 https://github.com/GeekyAnts/geeklegoWrote 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/geekyants/geeklego/figma-sync)<a href="https://agentmods.dev/skills/geekyants/geeklego/figma-sync"><img src="https://agentmods.dev/badge/skills/geekyants/geeklego/figma-sync/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/geekyants/geeklego/figma-sync"><img src="https://agentmods.dev/badge/skills/geekyants/geeklego/figma-sync.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 | $0.00268 | $0.06754 |
| Opus 5 | $0.00134 | $0.03377 |
| Sonnet 5 | $0.00054 | $0.01351 |
| Haiku 4.5 | $0.00027 | $0.00675 |
Grade A, and why
figma-sync 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 10d 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 — 675 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Sync — Geeklego Design System
Two scenarios, one direction: code → Figma. This skill is a Design System Auditor + Token Sync Engine — it reads the current Figma state before writing anything, audits it against the CSS, and produces a structured report of every change made.
| Scenario | What it does |
|---|---|
| Sync Design System | Reads a CSS file, audits Figma's current variables + text styles, diffs and reconciles only what's missing or wrong, then reports in a structured six-section format |
| Sync Component | Checks required tokens exist first, then builds a full Figma component (auto-layout, variants, variable bindings) from a React component |
The design system follows a strict 3-tier token chain:
Primitive (raw values) → Semantic (purpose aliases) → Component (per-component aliases)
Figma must mirror this hierarchy exactly using variable aliases. Never skip a level. Never hardcode a value.
Scope of Sync
Understanding what each trigger phrase does and does NOT touch prevents accidental writes.
| Trigger | Writes to Figma | Never writes to |
|---|---|---|
"sync my design system" |
01 · Primitives, 02 · Semantic, Text Styles |
03 · Component (read for audit only) |
"sync [component name]" |
03 · Component for that component only |
Any other component's tokens |
"nuke and recreate" |
All three collections + Text Styles | (full rebuild — nothing excluded) |
Rule: Component token blocks in the CSS are always parsed for audit inventory, but during a design system sync they are never written. Writes to 03 · Component happen only when the user explicitly requests a component sync.
Pre-flight (Both Scenarios)
Before doing anything, verify the Figma connection:
- Call
figma_get_status - Confirm
transport.websocket.available: trueand a connected file - If not connected — tell the user to open the Figma Desktop Bridge plugin and retry
Do NOT proceed if Figma is not connected.
What ships with it
2 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.
- 10d ago First seen · 675 lines · 0 tokens per session scan A ed25d56c3c2d
figma-sync is a skill published in the GitHub repository GeekyAnts/geeklego (5 stars, last pushed 2mo ago), licensed MIT. It adds 268 tokens to every session and 6,754 once invoked, about $0.0013 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.