figma

A connection between an AI coding assistant and Figma, a collaborative design and whiteboard app. It can read design files, render screenshots, inspect styles and variables, and support design-related workflows.

In plain words
What is it for?
Inspecting Figma files and FigJam boards, rendering design screenshots, reading design tokens, importing web pages as Figma designs, generating diagrams, and linking designs with code.
Why use it?
It gives the coding assistant the design details needed to understand or reproduce a Figma design instead of relying on guesswork.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/xyruscode/ai-sync/figma
Any agent
npx skills add XyrusCode/ai-sync --skill figma
Clone the repo
git clone --depth 1 https://github.com/XyrusCode/ai-sync

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00668
Opus 5 $0.00013 $0.00334
Sonnet 5 $0.00005 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured yesterday against content hash 5410628fd23c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

skills/figma/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figma Design Skill

Purpose: Connect to Figma via the Figma MCP server to read design context, generate new designs, and automate Figma workflows.


Prerequisites

  • Figma MCP must be configured in opencode.json with type: "remote" and url: "https://mcp.figma.com/mcp"
  • OAuth must be completed (browser-based auth flow)

Available Tools

Tool Purpose
get_screenshot Render a node as PNG (supports Figma design, FigJam, Slides)
get_design_context Fetch design structure, layers, styles, text from a Figma file
get_metadata Get file metadata (name, last modified, etc.)
get_variable_defs List design token variables and their values
get_figjam Retrieve FigJam board content
get_code_connect_map View existing code-to-design mappings
get_code_connect_suggestions Get AI suggestions for code connect mappings
get_context_for_code_connect Get context data needed for code connect
whoami Show current authenticated Figma user
generate_figma_design Capture/import a web page as a Figma design
generate_diagram Generate a diagram in Figma/FigJam
add_code_connect_map Link a code component to a Figma node
send_code_connect_mappings Batch-upload code connect mappings
use_figma General-purpose read/write — create/edit/delete any Figma object
get_libraries List available design system libraries
search_design_system Search design system components and styles
create_new_file Create a new Figma file
upload_assets Upload image assets to Figma

Common Workflows

Design-to-Code

  1. get_design_context with a Figma file URL/node ID
  2. Implement the component matching the design specs
  3. add_code_connect_map to link code back to the Figma node

Code-to-Design

  1. Build a UI component
  2. generate_figma_design to create a matching Figma frame
  3. Refine visually in Figma

Design System Sync

  1. get_libraries + search_design_system to find components
  2. get_variable_defs to read design tokens
  3. Generate component code matching the tokens
  4. use_figma to update variables/styles if needed

Read the full file on GitHub · 75 lines

Changes

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.

  1. yesterday First seen · 75 lines · 26 tokens per session scan A 5410628fd23c

Subscribe to this mod's changes

figma is a skill published in the GitHub repository XyrusCode/ai-sync (2 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 668 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.