figma-content-extractor

figma-content-extractor is an agent for Claude Code from adobecom/da-express-milo. It costs 0 tokens per session (1,033 once invoked), scanned A, original, Apache-2.0.

A procedure for reading the text and structure of one Figma design frame. Figma is a tool for creating interface designs.

In plain words
What is it for?
It is for extracting ordered, classified content from a Figma frame using its design data and a screenshot.
Why use it?
It removes the need to manually copy visible text and decide which parts are headings, body text, buttons, or other content.

Agent for Claude Code

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 agents/adobecom/da-express-milo/figma-content-extractor
Clone the repo
git clone --depth 1 https://github.com/adobecom/da-express-milo

Made for: Claude Code.

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 figma-content-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/adobecom/da-express-milo/figma-content-extractor.svg)](https://agentmods.dev/agents/adobecom/da-express-milo/figma-content-extractor)
Your own site
<a href="https://agentmods.dev/agents/adobecom/da-express-milo/figma-content-extractor"><img src="https://agentmods.dev/badge/agents/adobecom/da-express-milo/figma-content-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,033 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 $0.00000 $0.01033
Opus 5 $0.00000 $0.00517
Sonnet 5 $0.00000 $0.00207
Haiku 4.5 $0.00000 $0.00103

Measured 5d ago against content hash 92becbc9f52d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

figma-content-extractor 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.

.claude/skills/author-page-from-figma/agents/figma-content-extractor.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figma Content Extractor Subagent

Delegated from Phase 3 of the main SKILL.md. Extracts structured content from a single Figma frame.


Inputs

  • Figma frame URL (fileKey and nodeId)
  • Viewport label (mobile, tablet, or desktop — for reference only)

Extraction procedure

Step 1 — Get design context

Use Figma MCP get_design_context with the provided fileKey and nodeId. Also use get_screenshot to capture a visual reference.

Step 2 — Identify and classify text elements

Scan the design context for all text elements. For each, determine:

  1. Content: the visible text string.
  2. Classification: use visual heuristics from references/token-mapping.md. Express Figma files do not expose --s2a-typography-* tokens — classify by font size, weight, and position.
  3. Position: vertical position within the frame determines order (top to bottom).

Classify each text element as:

  • Eyebrow: small text (10–13px), often uppercase or letter-spaced, appearing above the heading.
  • Heading: largest bold text. Note the font size and map to a heading level using the token-mapping reference.
  • Body: medium text below the heading. Note font size for size class.
  • Link / CTA: text inside button-shaped elements or underlined interactive text. Record display text and CTA style:
    • Primary (filled button) → <strong><a>
    • Secondary (outline button) → <em><a>
    • Plain (text link) → bare <a>

Document any elements where heuristics were needed.

Step 3 — Identify media elements

  • Icons: small graphic ≤ 48px, typically above or beside the eyebrow/heading. Look for containers with data-node-id wrapping multiple layers or SVG. Record the parent icon node ID — do not use individual child layer URLs. Phase 5 exports the composite SVG via use_figma + exportAsync.

  • Background: the largest visual behind the content.

    • Color: extract the CSS color string (hex, rgb, gradient).
    • Image: record the Figma asset URL and node ID.

Read the full file on GitHub · 136 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 · 136 lines · 0 tokens per session scan A 92becbc9f52d

Subscribe to this mod's changes

figma-content-extractor is an agent published in the GitHub repository adobecom/da-express-milo (6 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,033 tokens. 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.