An accessibility checker for Figma designs based on WCAG 2.2, a set of web accessibility guidelines. It checks contrast, text size, touch-target size, and missing text alternatives, then can annotate issues in Figma.

Use it to scan Figma frames, review text and interactive elements, and mark potential WCAG violations for correction.

It helps identify design problems that may make an interface difficult to use for people with disabilities before development begins.

How renfei-design/Figma-AI-Bridge configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to renfei-design/Figma-AI-Bridge. 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/renfei-design/Figma-AI-Bridge/main/.github/skills/a11y-audit/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/renfei-design/Figma-AI-Bridge

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/renfei-design/figma-ai-bridge/a11y-audit/github.svg)](https://agentmods.dev/skills/renfei-design/figma-ai-bridge/a11y-audit)

Your own site

<a href="https://agentmods.dev/skills/renfei-design/figma-ai-bridge/a11y-audit"><img src="https://agentmods.dev/badge/skills/renfei-design/figma-ai-bridge/a11y-audit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/renfei-design/figma-ai-bridge/a11y-audit"><img src="https://agentmods.dev/badge/skills/renfei-design/figma-ai-bridge/a11y-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,653 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.

Model	Per session	Once invoked
Fable 5.1	$0.00076	$0.01653
Opus 5	$0.00038	$0.00826
Sonnet 5	$0.00015	$0.00331
Haiku 4.5	$0.00008	$0.00165

Measured 11d ago against content hash 8d798b9c87aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

a11y-audit 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 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/a11y_check.py, tests/test_a11y_check.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.github/skills/a11y-audit/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figma Accessibility Audit

Scan Figma frames for WCAG 2.2 accessibility violations and annotate issues directly. Be fast — scan, analyze, present, annotate.

Prerequisites

figma-ai-bridge plugin running in Figma and connected
Helper scripts:
- scripts/figma_cmd.mjs <channel> <command> [paramsJSON] — single command
- .github/skills/a11y-audit/scripts/a11y_check.py — offline analysis
Reference: .github/skills/a11y-audit/references/wcag-criteria.md
Use FIGMA_TIMEOUT_MS=30000 for scan commands, FIGMA_TIMEOUT_MS=60000 for large trees

Workflow — Do This Quickly

1. Scan text nodes

Get the selection, then scan all text nodes:

FIGMA_TIMEOUT_MS=30000 node scripts/figma_cmd.mjs <ch> scan_text_nodes '{"nodeId":"<id>"}' > /tmp/a11y_text_scan.json

Returns {textNodes: [{id, name, characters, fontSize, fontFamily, fontStyle, width, height, x, y, path, depth}]}.

2. Scan interactive elements

Scan for component instances and frames (potential buttons/controls):

FIGMA_TIMEOUT_MS=30000 node scripts/figma_cmd.mjs <ch> scan_nodes_by_types '{"nodeId":"<id>","types":["INSTANCE","COMPONENT"]}' > /tmp/a11y_components.json

Returns {matchingNodes: [{id, name, type, bbox: {x, y, width, height}}]}.

3. Enrich with full node info

Batch-fetch details including fills and parent background colors:

FIGMA_TIMEOUT_MS=60000 node scripts/figma_cmd.mjs <ch> get_nodes_info '{"nodeIds":["<id1>","<id2>",...]}' > /tmp/a11y_node_details.json

For each text node, also fetch its parent node(s) to find the background color. Walk up the tree: get the text node's parent from get_node_info, check if it has a solid fill. If not, get that node's parent. Stop at 3 levels or when a solid fill is found.

Efficient approach: Use get_node_info on the root frame with full children — the nested children array includes fills for all descendants, so you can walk the tree in one call for background resolution.

4. Analyze (offline)

Read the full file on GitHub · 160 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

11d ago First seen · 160 lines · 76 tokens per session scan A 8d798b9c87aa

Subscribe to this mod's changes

a11y-audit is a skill published in the GitHub repository renfei-design/Figma-AI-Bridge (16 stars, last pushed 6mo ago), licensed MIT. It adds 76 tokens to every session and 1,653 once invoked, about $0.0004 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.

Design and UX agentic-ai ai design-skills design-tools figma figma-plugin

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-AI-Bridge: Skill for Claude Code