Claude
Auto-triggering skills
Two skills in your Claude Code skills folder or on claude.ai. The one surface where the rules fire on matching work without being asked.
ADA Conformance Pack
Fix accessibility in the code, not the widget.
One accessibility review system that runs inside the AI tool you already use. Auto-triggering skills in Claude, a router for Cursor and Codex, prompts for any chat. It audits and fixes WCAG in your own repo, and tracks the rules as they move. Plain files with no telemetry and no network calls of their own.
Annual license. Web, iOS, Android, desktop, enterprise internal tools. If it renders a UI, the rules apply.
Why AI-built code fails WCAG
3,117
Federal website accessibility lawsuits filed in 2025, up 27 percent from 2024. Better than one in three of the top 500 e-commerce retailers got sued that year alone. (Seyfarth, UsableNet.)
72%
Engineering leaders at 30 million dollar-plus orgs who say AI-assisted development raised their compliance risk. (Deque, July 2026.) And 35 of 37 leading AI models ship critical and serious accessibility issues by default. (GAAD Foundation AIMAC benchmark, via Deque.)
2
Times the federal accessibility rules moved in 2026 alone: DOJ in April, HHS in May. The ground under the deadline shifts, so a one-time audit is stale the day it lands.
One system, three ways to run it
The same rules, wherever you work. In Claude they fire on their own. In Cursor, Codex, and other coding agents a router file includes them with the work. In any chat, they are prompts you paste. Install more than one if you like; they all ship the same rules.
Cursor, Codex, Copilot, and other coding agents
An AGENTS.md router
One router file points your agent at the same rule modules, included with the work. A Cursor rules file, a Copilot instructions file, one setting for Gemini CLI.
ChatGPT, or any chat
Standalone prompts
The seven audit prompts, pasted straight into any chat window, nothing installed. Your code goes to that provider, so use this where that is allowed.
Under all three formats: 6 rule modules and 7 audit prompts. The modules split accessibility into the two jobs it actually is. How a thing looks: contrast, color, type, target size, focus, motion, dark mode, and token enforcement that bakes a passing contrast ratio into your design tokens, so a failing pair cannot be assembled by hand. How a thing is built: semantic HTML first, ARIA only where HTML falls short, keyboard, focus, live regions, forms. Plus mobile, desktop, and a shared research system carrying the severity scale and the current regulatory deadlines. The prompts run the review: 00 routes a whole audit and names what it skipped, 06 writes the VPAT rows procurement asks for.
How the WCAG audit runs in your repo
Run prompt 02 on a component, or let prompt 00 route a whole review and skip what does not apply. Findings come rated by severity with the fix in place, and every one says what it verified and what a human still has to check. It works downstream of any scanner: your scanner finds the issue, this ships the fix.
Sample review output
> paste prompt 02, the full component audit, on Dialog.tsx
Dialog.tsx, web, AA. Blocker 1, Critical 0, Major 1, Minor 0.
Human verification outstanding: 1.
1. Close control is a div with an onclick, no keyboard support
Criterion: WCAG 2.1.1 Keyboard, A (APG Dialog)
Severity: Blocker
Fix: use a native button, close on Escape, return focus to
the element that opened the dialog
Verify (agent): tab to it, confirm Enter and Escape both fire
2. Icon-only close button has no accessible name
Criterion: WCAG 4.1.2 Name, Role, Value, A
Severity: Major
Fix: add aria-label="Close" to the button
Verify (agent): read the accessibility tree, confirm the name
Verify (human): hear the button announced in a screen readerSeverity-rated per criterion, so findings translate into the Supports, Partially Supports, and Does Not Support rows a VPAT asks for when procurement wants one.
What a report looks like
This site runs behind an accessibility gate that fails on any violation, across 9 pages, 2 viewports, and 2 themes. Here is its last run, published in full, numbers generated by the run itself rather than typed in by us.
tokenstoagents.com, WCAG 2.2 AA 2026-08-02
0 violations
808 checks passed
36 flagged for human review
34 rules exercised
That third number is the one that matters. A tool that reports zero problems and zero uncertainties is lying to you. Automated rules catch 30 to 40 percent of real accessibility issues. The other 60 gets flagged for a human, because deciding whether a heading actually describes the section under it is not something a rules engine can do.
Read the full report. Every finding names the rule, the level, a severity from Blocker to Minor, the exact element, and the fix, mapped per criterion so it translates into the Supports and Partially Supports rows a VPAT asks for.
ADA, Section 504, and EAA deadlines
Current as of July 29, 2026
| Rule and who it covers | Standard named | Date |
|---|---|---|
| DOJ ADA Title II, public entities with population 50,000 or more | WCAG 2.1 AA | April 26, 2027 |
| DOJ ADA Title II, public entities under 50,000 and all special districts | WCAG 2.1 AA | April 26, 2028 |
| HHS Section 504, health programs with 15 or more employees | WCAG 2.1 AA | May 11, 2027 |
| HHS Section 504, health programs under 15 employees | WCAG 2.1 AA | May 10, 2028 |
| EU Accessibility Act, wherever your customers are | EN 301 549 (WCAG 2.1 AA) | In force since June 28, 2025 |
The original April 24, 2026 Title II deadline never took effect. DOJ extended both dates by one year on April 20, 2026 (Interim Final Rule, 91 FR 20902), and HHS extended its Section 504 dates in 2026 as well. On May 21, 2026 the National Federation of the Blind sued DOJ and HHS to vacate those extensions. That case is pending, so these dates are under active litigation and could move again in either direction. A new EN 301 549 version that imports WCAG 2.2 is expected.
This is not legal advice. Confirm your own cohort and obligations with counsel.
The deadlines moved twice in 2026. Your renewal keeps the pack current with them.
Pricing and annual license
Individual
$149 per year
- All three formats: Claude skills, the coding-agent router, the chat prompts
- The full sourced research system
- Every update while your license is active
- License key, one seat
Renewal ships updated rules whenever WCAG, EN 301 549, or the DOJ and HHS dates change, plus refreshed date-stamped research and a changelog.
Get the individual licenseTeam
from $749 per year
- Everything in Individual
- $74.90 per seat, 10-seat minimum. Add seats as the team grows.
- The team kit: a client audit report generator, and the workflow that installs the pack once per client repo instead of once per person.
- Unlimited client projects
- Priority email support, answered ahead of individual licenses
Same renewal deliverable as Individual: updated rules on every change, refreshed research, and a changelog, for every seat.
Get the team license14-day money-back, no argument. Founding price, locked while your license stays active.
Prices in USD. Tax and VAT are handled at checkout by Polar, our merchant of record, who issues your receipt and invoice. You get all three formats plus the research folder, downloaded the moment you pay.
One manual audit of a small site runs 3,000 to 7,000 dollars and goes stale the day it lands. The pack re-audits every review you run.
Enterprise
A custom rule profile for your design system, VPAT and ACR workflows your procurement team expects, named support with a 2-business-day SLA, and net-30 terms. Rolled out and governed at your scale.
For teams that need IT approval
- Plain-text Markdown files your IT team can read line by line before anything is installed.
- The pack makes no network calls of its own, sends no telemetry, and gives us no access to your code.
- It runs inside the AI environment you already approved. The chat prompts, like any chat, send your code to that provider; the Claude and coding-agent formats stay where your agent already runs.
The full security architecture, the enterprise pinning story, and the requirements are on the install and IT-approval page.
WCAG and ADA questions
What exactly do I get when I buy?
One rule set, delivered three ways, downloaded from Polar the moment you pay. Auto-triggering skills for Claude (ada-visual and ada-aria, plain Markdown), an AGENTS.md router for Cursor, Codex, and other coding agents, and the seven audit prompts standalone for any chat. Plus the dated research the rules check their findings against, a license key, and every update while the license is active. No app to run, no account on our servers, nothing but files you can read.
Why is the license annual?
Because the ground moves. DOJ extended the Title II dates in April 2026, HHS extended its Section 504 dates weeks later, and the National Federation of the Blind is suing to undo both. Your renewal is a re-verification: updated skills and refreshed, date-stamped research whenever WCAG, EN 301 549, or the DOJ and HHS dates change. Current as of July 29, 2026, and under active litigation.
Does this make us compliant?
No, and anyone who tells you a tool can is selling you a lawsuit. The pack finds and fixes conformance issues in your code and rates them by severity. Compliance is a legal determination about your whole product and process, not a checkmark a skill hands you. This is not legal advice. Confirm your obligations with counsel.
What about accessibility overlay widgets?
An overlay is a script you paste in that promises instant compliance and does not deliver it. Sites running overlays drew hundreds of accessibility lawsuits in 2025, and the FTC's one million dollar order against an overlay vendor for deceptive compliance claims became final in April 2025. The pack does the opposite: it changes the code in your repo, where the problems live, and never touches your production site.
Do I need Claude to run this?
No. Claude is the first-class path: the skills fire on matching work without being asked, and it is what we test against every release. For Cursor, Codex, Copilot, and other coding agents, an AGENTS.md router includes the same rules with the work. For any chat, the audit prompts are standalone, paste and go. The one thing only Claude does is trigger on its own; everywhere else you bring the rules to the work. The install page walks all three.
Does this work with my framework?
Yes. The rules are about accessibility, not your stack: contrast ratios, keyboard contracts, semantic structure, target sizes. Contrast math does not care which framework computed the color. React, Swift, Kotlin, Flutter, or plain HTML, the rules are the same.
How is this different from axe or Lighthouse?
Those are scanners. They tell you a contrast ratio failed on line 40. The pack works downstream of that: it reads the finding, decides what the fix should be in your system, and writes it. Automated scanners also miss most real issues, because most accessibility failures are judgment calls a rules engine cannot make: is this the right heading level, does this button name describe what it actually does, does this focus order match the reading order. Keep your scanner. This handles the part it cannot.
Which platforms does it cover?
Web, iOS, Android, desktop, and enterprise internal tools. The design layer translates every size and contrast rule into the right units per platform, CSS pixels, iOS points, Android dp, and the code layer routes native work to platform-specific modules instead of applying web ARIA rules where they do not belong.
Can I use it on client work?
Yes, on both tiers. An individual license covers one named person on any project they work on, including client projects. A team license covers everyone at one organization who uses the pack, one seat each with a 10-seat minimum, across unlimited client projects. What neither license allows is reselling or redistributing the pack itself as a product.
How does the team license count seats and client sites?
Each person at your organization who uses the pack takes a seat. Checkout has a 10-seat minimum, and you can add seats at any time as the team grows. Client projects are unlimited: committing the pack into a client repo during an engagement is allowed and intended, and when the engagement ends the pack comes out unless that client holds their own license.
What happens when a license lapses?
Updates and downloads stop. The files you already have keep working, because they run inside your own environment. You just stop getting the refreshed research and the rule-change updates that are the whole reason it is annual.
Will my security team approve this?
It is the easiest review they will do all quarter. The pack is static plain-text files that run inside the AI environment you already approved. It has no server, makes no network calls of its own, sends no telemetry, and gives us no access to your code. Your team can read every rule before installing it. The install page has the full architecture statement to forward them.
What is your refund policy?
14 days, money back. If the pack is not what you needed, email us within 14 days of purchase for a full refund. You keep anything you already fixed with it. Telling us why is optional, but it helps us improve the pack.
How do I buy for a team that needs a PO or an invoice?
Checkout issues a receipt and invoice automatically through Polar, our merchant of record, which covers most team purchases. If you need a purchase order, net-30 terms, a W-9, or a quote on letterhead for a p-card file, that is the enterprise tier. Tell us what your procurement process needs and we will work to it.