extract-figma-assets

extract-figma-assets is a skill for Claude Code from a8cteam51/claude-code-plugins. It costs 113 tokens per session (1,141 once invoked), scanned A, original, MIT.

A tool that connects to the Figma desktop app and exports assets and design context for a selected frame or node. Dev Mode MCP is Figma’s local connection for sharing design information with coding tools.

In plain words
What is it for?
Use it to retrieve referenced images, a screenshot, design context, variables, metadata, and other details for a selected Figma node.
Why use it?
It removes repetitive copying and downloading when implementing a Figma design in code.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the figma-extract plugin — 1 skill, 1 command shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add a8cteam51/claude-code-plugins
Claude Code
/plugin install figma-extract

Made for: Claude Code.

Or install figma-extract, the plugin that ships this one along with the rest of its 1 skill, 1 command.

Wrote 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.

agentmods badge for extract-figma-assets

README.md
[![agentmods](https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/extract-figma-assets.svg)](https://agentmods.dev/skills/a8cteam51/claude-code-plugins/extract-figma-assets)
Your own site
<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/extract-figma-assets"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/extract-figma-assets.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 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 5.1 $0.00113 $0.01141
Opus 5 $0.00056 $0.00571
Sonnet 5 $0.00023 $0.00228
Haiku 4.5 $0.00011 $0.00114

Measured 5d ago against content hash cff5a14f808d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

extract-figma-assets 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 5d 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.

plugins/figma-extract/skills/extract-figma-assets/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract images & design context from Figma

This skill pulls the assets and design context for a Figma selection out of Figma desktop's local Dev Mode MCP server (the HTTP server at http://127.0.0.1:3845/mcp) and writes them to a folder on disk.

A bundled, zero-dependency Node script (scripts/extract-figma-assets.mjs) owns the whole flow: it opens an MCP session, calls get_design_context, get_variable_defs, get_metadata, and get_screenshot, parses the const imgFoo = "http://localhost:3845/assets/<hash>.<ext>" declarations out of the returned code, and downloads each asset. Do not reimplement any of this by hand or by calling the MCP tools yourself — just run the script and report what it produced.

Prerequisites

  • Figma desktop must be running with Dev Mode MCP enabled (Figma → Preferences → "Enable Dev Mode MCP server"), and
  • the user must have selected the frame/node they want extracted (unless they give you an explicit node id or Figma URL).
  • Node.js 20+ must be on PATH.

If the script reports Nothing is selected, tell the user to select a frame in Figma desktop (or pass a node id / URL) and try again — don't retry blindly.

How to run it

Run the script with Bash. Use ${CLAUDE_PLUGIN_ROOT} so the path resolves regardless of where the plugin is installed:

node "${CLAUDE_PLUGIN_ROOT}/scripts/extract-figma-assets.mjs" --out <dir> --json

Decide the arguments from what the user asked:

  • Current selection (default): pass no --node. This is the right choice for "extract images from my current selection".
  • Specific node: if the user pastes a Figma URL (e.g. one containing ?node-id=1-2) or a node id like 1:23, pass it with --node <id|url>.
  • Output directory: default to ./figma-extract in the current working directory. If the user names a destination (e.g. "into ./assets"), pass it via --out. Mention the resolved path in your summary.
  • Design context: by default the script saves images only (assets + screenshot). Only pass --context (alias --full) if the user also wants the design-context files (code.tsx / variables.json / metadata.xml) — e.g. they mention variables, tokens, the generated code, or "everything".
  • Always pass --json so you get a machine-readable manifest on stdout to summarise from. Progress lines go to stderr.

Read the full file on GitHub · 92 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. 5d ago First seen · 92 lines · 113 tokens per session scan A cff5a14f808d

Subscribe to this mod's changes

extract-figma-assets is a skill published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 8d ago), licensed MIT. It adds 113 tokens to every session and 1,141 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens