agentic-design-system: Skill for Claude Code

.claude/skills/verify-component-figma/SKILL.md

verify-component-figma is a skill for Claude Code from brianmontanaweb/agentic-design-system. It costs 119 tokens per session (1,579 once invoked), scanned A, original, MIT.

A visual check that compares a Storybook component rendering with its matching Figma design node. It creates a pixel difference percentage and saves a diff image.

In plain words
What is it for?
Use it when checking whether a component matches Figma, provided the Figma node link and required rendering access are available.
Why use it?
It catches visual mismatches that may be missed by checking only colors, spacing, typography, or code values.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is brianmontanaweb/agentic-design-system's own configuration. It tells Claude Code how to work on agentic-design-system itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentic-design-system configures →

Reuse

Borrowing it

Nothing to install: this file belongs to brianmontanaweb/agentic-design-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/brianmontanaweb/agentic-design-system/main/.claude/skills/verify-component-figma/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/brianmontanaweb/agentic-design-system

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 verify-component-figma

README.md
[![agentmods](https://agentmods.dev/badge/skills/brianmontanaweb/agentic-design-system/verify-component-figma/github.svg)](https://agentmods.dev/skills/brianmontanaweb/agentic-design-system/verify-component-figma)
Your own site
<a href="https://agentmods.dev/skills/brianmontanaweb/agentic-design-system/verify-component-figma"><img src="https://agentmods.dev/badge/skills/brianmontanaweb/agentic-design-system/verify-component-figma/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 verify-component-figma

Your own site · 80×15
<a href="https://agentmods.dev/skills/brianmontanaweb/agentic-design-system/verify-component-figma"><img src="https://agentmods.dev/badge/skills/brianmontanaweb/agentic-design-system/verify-component-figma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00119 $0.01579
Opus 5 $0.00060 $0.00790
Sonnet 5 $0.00024 $0.00316
Haiku 4.5 $0.00012 $0.00158

Measured 9d ago against content hash 0a7409d54f32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-component-figma scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -H "X-Figma-Token: $FIGMA_TOKEN" \
.claude/skills/verify-component-figma/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Component Against Figma

Render a component's Figma design node to an image, screenshot the matching Storybook story, pixel-diff the two, and report the result. This is a visual check — it complements (does not replace) the data check in docs/best-practices.md section 8 (colors/spacing/typography extracted as values). A component can pass the data check and still fail this one if e.g. line-height or padding renders differently than the extracted values suggest.

Parse $ARGUMENTS as <ComponentName> <core|agents> <FigmaNodeURL> [storyExportName].


Gotchas

  • A Figma render needs credentials one way or another. Either a connected Figma MCP server that exposes an image/render tool, or a personal access token in FIGMA_TOKEN for the REST fallback in Step 2. If neither is available, stop and tell the user which one to set up — do not guess or skip this step silently.
  • The Figma node link is required, not optional, for this skill — unlike /update-component's Figma step, there's nothing meaningful to compare without it. If the user hasn't provided one, ask for it before proceeding.
  • storyExportName disambiguates which variant to compare. A Figma component node usually corresponds to one specific variant (e.g. "Solid / Medium"), not the whole component. If the user didn't say which story export matches the Figma node, ask — don't default to the first export in the file, since that's frequently the wrong visual state to compare.
  • Storybook must be running against http://localhost:6006 for the Playwright screenshot step. Check before assuming; start it if it's not up.
  • Dimension mismatches make the pixel diff meaningless. scripts/figma-diff.ts compares only the overlapping region and flags a mismatch explicitly — always surface that flag in the report rather than only reporting the diff percentage.
  • This is exploratory tooling, not CI. Output images are gitignored scratch artifacts (.figma-diff/), not committed baselines like apps/storybook/__snapshots__. Don't try to wire this into test:visual.

Read the full file on GitHub · 119 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. 9d ago First seen · 119 lines · 119 tokens per session scan A 0a7409d54f32

Subscribe to this mod's changes

verify-component-figma is a skill published in the GitHub repository brianmontanaweb/agentic-design-system (3 stars, last pushed 19d ago), licensed MIT. It adds 119 tokens to every session and 1,579 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

design-qa-checklist

Build a QA checklist for verifying that a build matches the design. Use at implementation review. For the spec engineers build from, use handoff-spec.

Owl-Listener/designer-skills · 37 tokens

design-qa

Set up or run design QA gates — token + hardcoded-value lint, automated a11y (axe), contrast, visual regression across variants/states/themes/RTL, and the manual a11y checklist. Use when the user wants CI quality gates, to prevent design regressions, or to QA a component/screen before shipping.

plugin87/ux-ui-agent-skills · 71 tokens

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…

productdevbook/shadcn-htmx · 90 tokens

seed-verify-figma-mcp-transports

A verification tool for Figma MCP tools that runs the same request through REST and WebSocket connections and compares the answers. MCP is a way for an AI agent to call external tools; REST and WebSocket are two ways to communicate with a service.

daangn/seed-design · 38 tokens

conversational-ux

Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.

Owl-Listener/designer-skills · 43 tokens

platform-conventions

Design to iOS and Android conventions — what each OS mandates, where they diverge, and when to unify. Use when shipping native apps. For breakpoint adaptation use responsive-design; for matching competitor patterns use jakobs-law (interaction-design).

Owl-Listener/designer-skills · 55 tokens