extract

A command for saving images, a screenshot, and design details from a selected Figma element to a local folder. It can use the current selection or a supplied Figma node ID or URL.

In plain words
What is it for?
Use it to extract assets from a Figma selection, optionally including generated code, variables, or metadata.
Why use it?
It gathers the materials needed for design-to-code work in one step instead of requiring manual downloads from Figma.

Command

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 commands/a8cteam51/claude-code-plugins/extract
Clone the repo
git clone --depth 1 https://github.com/a8cteam51/claude-code-plugins
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 508 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 $0.00035 $0.00508
Opus 5 $0.00017 $0.00254
Sonnet 5 $0.00007 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured yesterday against content hash de4a0ad19307, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

plugins/figma-extract/commands/extract.md · 49 lines

What it actually says

/figma-extract:extract

Extract the images, screenshot, and design context for a Figma selection by running the bundled, zero-dependency extractor. All MCP transport, asset parsing, and downloading is delegated to ${CLAUDE_PLUGIN_ROOT}/scripts/extract-figma-assets.mjs — do not reimplement it or call the Figma MCP tools yourself. This command mirrors the extract-figma-assets skill; the skill's body has the full reference.

Inputs

Parse $ARGUMENTS (all optional):

  • A bare node id (1:23 / 1-23) or a Figma URL (contains ?node-id=…) → pass as --node <value>. If absent, the script uses the current selection in Figma desktop.
  • --out <dir> → output directory. If the user didn't specify one, default to ./figma-extract.
  • The script saves images + screenshot only by default. Pass --context (alias --full) through to the script only if the user also asks for the generated code, variables, or metadata.

Run

node "${CLAUDE_PLUGIN_ROOT}/scripts/extract-figma-assets.mjs" \
  [--node <id|url>] --out <dir> --json

Progress goes to stderr; a JSON manifest is printed to stdout.

Report

Summarise from the JSON manifest: number of assets downloaded (raster/svg split), any cached/failed counts, the absolute output path, and the image filenames.

If the script reports Nothing is selected, tell the user to select a frame in Figma desktop (or pass a node id / URL) and re-run — do not retry blindly. If counts.referenced is 0, say the selection referenced no placed images; the screenshot and design context were still saved.

Requires Figma desktop running with Dev Mode MCP enabled and Node.js 20+.

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 · 49 lines · 0 tokens per session scan A de4a0ad19307

Subscribe to this mod's changes

extract is a command published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 508 once invoked, about $0.0002 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.