agentmods.dev

talk-to-figma-design

talk-to-figma-design is a skill for Claude Code, Codex from richardplg2/figma-annotations. It costs 28 tokens per session (1,586 once invoked), scanned A, original, MIT.

A design-planning helper for Figma, a collaborative interface-design tool. It reads an exported Figma design prompt, combines it with information from Figma and the codebase, and produces a design specification for brainstorming.

In plain words
What is it for?
Use it to gather requirements from Figma, inspect related code, and prepare a design specification; it does not implement the code.
Why use it?
It turns design notes and existing project context into a clearer plan before implementation begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 11repo 5mo ago A scan 28 tokens original MIT

Good fit Use it to gather requirements from Figma, inspect related code, and prepare a design specification; it does not implement the code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richardplg2/figma-annotations/talk-to-figma-design
View source ↗ richardplg2/figma-annotations
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.

Any agent
npx skills add richardplg2/figma-annotations --skill talk-to-figma-design
Clone the repo
git clone --depth 1 https://github.com/richardplg2/figma-annotations

Made for: Claude Code, Codex.

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 talk-to-figma-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/richardplg2/figma-annotations/talk-to-figma-design/github.svg)](https://agentmods.dev/skills/richardplg2/figma-annotations/talk-to-figma-design)
Your own site
<a href="https://agentmods.dev/skills/richardplg2/figma-annotations/talk-to-figma-design"><img src="https://agentmods.dev/badge/skills/richardplg2/figma-annotations/talk-to-figma-design/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.

agentmods 80×15 button for talk-to-figma-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/richardplg2/figma-annotations/talk-to-figma-design"><img src="https://agentmods.dev/badge/skills/richardplg2/figma-annotations/talk-to-figma-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,586 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00028 $0.01586
Opus 5 $0.00014 $0.00793
Sonnet 5 $0.00006 $0.00317
Haiku 4.5 $0.00003 $0.00159

Measured 12d ago against content hash 55eedbd11a21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

talk-to-figma-design 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 12d 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.

skills/talk-to-figma-design/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

talk-to-figma-design

Collect Figma design requirements, enrich them with live Figma data and codebase analysis, then hand off to the brainstorming pipeline for implementation planning.

Trigger

User invokes /talk-to-figma-design after pasting a markdown prompt exported from the figma-annotations VS Code extension.

Arguments (all optional):

  • --channel <id> — override channel ID from prompt
  • --collection "<name>" — process only the named collection's items
  • <topic> — free text topic name for the spec file (default: derived from first frame name)

Prerequisites

  • cursor-talk-to-figma MCP server running (bun socket on port 3055)
  • Figma plugin active in the Figma file
  • GitNexus index available in the current project (optional — skipped gracefully if missing)

Workflow

Follow these steps in order. Do NOT skip steps. Do NOT implement any code — this skill only collects, enriches, and generates a spec.

Step 1: Parse Prompt

  1. Scan the conversation for the <!-- talk-to-figma-design --> marker
  2. If no marker found, tell the user: "No Figma design prompt found. Export collections from the figma-annotations VS Code extension first using 'Export Collections as Prompt'."
  3. Extract from the prompt:
    • Channel ID from the ## Connection section
    • Design frames with their nodeIds, names, types, dimensions, notes, and collection names
    • Code references with file paths, line ranges, language, code, notes, and collection names
  4. If --channel argument provided, use it instead of the prompt's channel ID
  5. If --collection argument provided, filter to only items from that collection

Step 2: Enrich from Figma MCP

Use the cursor-talk-to-figma MCP tools to gather detailed design data.

  1. Connect: Call join_channel with the resolved channel ID
  2. For each design frame nodeId:
    • Call get_node_info(nodeId) — capture children hierarchy, layout properties, auto-layout settings
    • Call scan_text_nodes(nodeId) — capture all text content within the frame
  3. Global design data:
    • Call get_styles() — capture color tokens, typography, effects
    • Call get_local_components() — capture available component library

Read the full file on GitHub · 164 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. 12d ago First seen · 164 lines · 28 tokens per session scan A 55eedbd11a21

Subscribe to this mod's changes

talk-to-figma-design is a skill published in the GitHub repository richardplg2/figma-annotations (11 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,586 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 2026-08-30.

Claude CodeDesign and UXai-assisted-developmentdesign-to-codefigmamcpvscode-extension
Related

Other skills, from other repositories

figma-codegen

Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…

awdr74100/figwright · 145 tokens

figma-build

Build a Figma design from code or a description — the reverse of figma-codegen. Reuses the connected file's existing design system (components, variables, styles) instead of drawing primitives with hardcoded values. Triggers whenever the user wants something created or updated IN Figma from code or a spec — e.g.…

awdr74100/figwright · 180 tokens

figma-design-handoff

Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to CSS Flexbox/Grid mapping, and visual regression with Applitools. Use when converting Figma designs to code, documenting component specs, setting up design-dev…

yonatangross/orchestkit · 76 tokens

screenshot-intake

Use when a user provides a URL or screenshot files and wants to build an app from them, or when starting /build-from-screenshot. Captures pages via Chrome DevTools or Playwright MCP, analyzes structure with Claude vision, and produces build-spec.json. Keywords: screenshot intake, URL capture, build spec, screenshot…

PMDevSolutions/Aurelius · 0 tokens

visual-qa-verification

Automated visual QA with pixel-level diff comparison, iterative fix loop, and cross-browser verification. Uses pixelmatch for programmatic screenshot comparison with region-based analysis. Covers responsive checks, Lighthouse audits, and accessibility validation. Keywords: verify app, visual QA, compare to Figma…

PMDevSolutions/Aurelius · 81 tokens

canva-intake

Structured discovery for Canva designs. Uses Canva AI Connector MCP to export screenshots, Claude vision to analyze page structure and components, and targeted user questions to produce a build-spec.json. Entry point for /build-from-canva pipeline. Keywords: Canva intake, build spec, Canva discovery, Canva interview…

PMDevSolutions/Aurelius · 0 tokens