accessibility-check

accessibility-check is an agent for Claude Code from adobecom/da-express-milo. It costs 0 tokens per session (771 once invoked), scanned A, original, Apache-2.0.

A browser-based accessibility audit for a web page or interface block, using axe-core and Playwright to check WCAG 2.2 AA rules at desktop and mobile sizes.

In plain words
What is it for?
Use it after visual testing to scan a block, review each reported issue, and fix remaining accessibility violations.
Why use it?
It finds accessibility problems that may prevent people from using the interface, such as poor contrast, missing focus indicators, or touch targets that are too small.

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/accessibility-check
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 accessibility-check

README.md
[![agentmods](https://agentmods.dev/badge/agents/adobecom/da-express-milo/accessibility-check.svg)](https://agentmods.dev/agents/adobecom/da-express-milo/accessibility-check)
Your own site
<a href="https://agentmods.dev/agents/adobecom/da-express-milo/accessibility-check"><img src="https://agentmods.dev/badge/agents/adobecom/da-express-milo/accessibility-check.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 771 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 $0.00771
Opus 5 $0.00000 $0.00385
Sonnet 5 $0.00000 $0.00154
Haiku 4.5 $0.00000 $0.00077

Measured 3d ago against content hash 445fb2c09ca4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

accessibility-check 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 3d 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/build-block-from-figma/agents/accessibility-check.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Check Subagent

This script is delegated from Phase 6 of the main SKILL.md. Run only after the visual comparison loop (Phase 5) is complete.


Target

WCAG 2.2 AA — full compliance. No violations, no incomplete checks left unresolved.


Tool

Uses @axe-core/playwright which is installed as a project dev dependency. Axe-core is injected into the page via Playwright MCP.


Procedure

  1. Navigate to the preview URL using Playwright MCP.
  2. Set viewport to 1360 px wide (desktop) for the initial scan.
  3. Inject and run axe-core scoped to the block's root element:
    const { AxeBuilder } = require('@axe-core/playwright');
    
    const results = await new AxeBuilder({ page })
      .include('.block-name')      // scope to the block
      .withTags(['wcag2a', 'wcag2aa', 'wcag22aa'])
      .analyze();
    
  4. Repeat the scan at mobile viewport (375 px) to catch responsive-specific issues (e.g. touch target sizes, focus visibility at small sizes).

Processing results

Violations (must fix)

For each violation in results.violations:

  1. Log the rule ID, impact level, description, and affected nodes.
  2. Fix the violation:
    • If it's a CSS issue (contrast, focus indicator, sizing), update the block's CSS file.
    • If it's an HTML/DOM issue (missing alt text, incorrect ARIA, missing labels), update the block's JS file (the JS is responsible for DOM manipulation at init time).
    • If it's an authoring issue (e.g. missing alt text on an <img> that came from the authored content), note it as an authoring concern but do not modify authored content.
  3. Re-run axe-core to confirm the fix.
  4. Repeat until zero violations.

Incomplete checks (review)

For each item in results.incomplete:

  • Assess whether the block can resolve it or whether it requires manual review (e.g. colour contrast on complex backgrounds).
  • If resolvable, fix it.
  • If not, document it in Obstacles Encountered.

Read the full file on GitHub · 101 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. 3d ago First seen · 101 lines · 0 tokens per session scan A 445fb2c09ca4

Subscribe to this mod's changes

accessibility-check is an agent published in the GitHub repository adobecom/da-express-milo (6 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 771 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.