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.
git clone --depth 1 https://github.com/ncklrs/claude-chrome-user-testingWrote 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.
[](https://agentmods.dev/commands/ncklrs/claude-chrome-user-testing/wcag-audit)<a href="https://agentmods.dev/commands/ncklrs/claude-chrome-user-testing/wcag-audit"><img src="https://agentmods.dev/badge/commands/ncklrs/claude-chrome-user-testing/wcag-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.
<a href="https://agentmods.dev/commands/ncklrs/claude-chrome-user-testing/wcag-audit"><img src="https://agentmods.dev/badge/commands/ncklrs/claude-chrome-user-testing/wcag-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00033 | $0.02343 |
| Opus 5 | $0.00016 | $0.01171 |
| Sonnet 5 | $0.00007 | $0.00469 |
| Haiku 4.5 | $0.00003 | $0.00234 |
Grade A, and why
wcag-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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WCAG Audit Command
Perform a comprehensive WCAG 2.1 accessibility audit on a web page to identify compliance issues and generate an actionable report.
Arguments
Parse the following from $ARGUMENTS:
--url <url>(required): URL to audit--level <a|aa>(optional): Conformance level to check (default: aa, which includes a)--format <format>(optional): Output format - summary | detailed | json (default: detailed)--save <filename>(optional): Save report to file--annotate(optional): Take annotated screenshots of violations
Prerequisites
This command requires:
- Claude running with
--chromeflag - Playwright MCP tools available
Audit Flow
Step 1: Initialize
- Navigate to the target URL using
browser_navigate - Wait for page to fully load
- Take initial accessibility snapshot with
browser_snapshot - Initialize counters for passed/failed criteria
Step 2: Run Level A Checks
Check these essential WCAG 2.1 Level A criteria:
1.1.1 Non-text Content
Check all images have appropriate alt text:
Use browser_evaluate to find:
- Images without alt attribute
- Images with empty alt on non-decorative images
- Background images conveying information without text alternative
Severity: Critical if functional images lack alt text
1.3.1 Info and Relationships
Check semantic HTML usage:
Use browser_snapshot to verify:
- Proper heading hierarchy (h1 → h2 → h3)
- Lists use ul/ol/li elements
- Tables have proper th/caption
- Form fields have associated labels
Severity: Major
1.3.2 Meaningful Sequence
Check reading order:
Use browser_evaluate to compare:
- Visual order vs DOM order
- CSS doesn't create confusing reordering
Severity: Major
2.1.1 Keyboard Accessible
Check all interactive elements work with keyboard:
Use browser_press_key to Tab through page:
- Can reach all interactive elements
- Buttons, links, form fields are focusable
- Custom widgets have keyboard support
Severity: Critical
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.
- 9d ago First seen · 414 lines · 33 tokens per session scan A 2ea7e5d812e2
wcag-audit is a command published in the GitHub repository ncklrs/claude-chrome-user-testing (19 stars, last pushed 8mo ago), licensed MIT. It adds 33 tokens to every session and 2,343 once invoked, about $0.0002 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.
Other commands, from other repositories
apply-design-md
Consume the project's design contract — a .design file or DESIGN.md — and thread its tokens through UI code (CSS, Tailwind, or design-system components).
agentation-fix
Session-2 fix loop for Agentation — read structured annotations from the dev overlay and apply targeted UI fixes.
accessibility-check
WCAG 2.2 AA accessibility compliance check.
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
motion-designer
Use when animation feels wrong. Transitions too slow or too bouncy, motion with no purpose, blanket transitions on every property, no reduced-motion support, or animation that drops frames.
spacing-layout-specialist
Use when spacing looks arbitrary. Padding and margins off any scale, inconsistent gaps between the same components, no grid underneath, or a layout that needs a denser mode.