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.
npx skills add 0xDarkMatter/claude-mods --skill a11y-opsgit clone --depth 1 https://github.com/0xDarkMatter/claude-modsWrote 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/skills/0xdarkmatter/claude-mods/a11y-ops)<a href="https://agentmods.dev/skills/0xdarkmatter/claude-mods/a11y-ops"><img src="https://agentmods.dev/badge/skills/0xdarkmatter/claude-mods/a11y-ops/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/skills/0xdarkmatter/claude-mods/a11y-ops"><img src="https://agentmods.dev/badge/skills/0xdarkmatter/claude-mods/a11y-ops.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 | $0.00131 | $0.02910 |
| Opus 5.5 | $0.00052 | $0.01164 |
| Sonnet 5.5 | $0.00026 | $0.00582 |
| Haiku 4.5 | $0.00013 | $0.00291 |
Grade A, and why
a11y-ops 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 1mo 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a11y-ops
Accessibility stopped being a quality preference and became a legal requirement with dates attached. It is also, unhelpfully, a domain where the tooling everyone reaches for finds well under half the problems — so the work is mostly about knowing where automation stops.
Helps with
"Is our site compliant?" — a question with a real answer that depends on which jurisdiction, which standard version, and which deadline applies to that client.
An audit that needs to find real failures rather than produce a score. Vendor "94% accessible" numbers correspond to nothing in the standard.
A component library where every custom control is mouse-only, because a <div>
replaced a <button> and nothing replaced what the <button> was doing.
Forms that lose conversions from screen reader and keyboard users: placeholders
used as labels, errors signalled only in red, no autocomplete.
outline: none shipped across a design system, leaving keyboard users with no
idea where they are.
A modal, dropdown or date picker that traps focus, or drops it, or never returns it to the trigger.
Writing an accessibility statement that is honest enough to be defensible rather than an overclaim that creates its own liability.
Wiring accessibility into CI so a fix stays fixed instead of being re-bought at the next audit.
The two things that decide everything
1. Automated tooling finds roughly 30–40% of WCAG failures. Every plan follows from this. A green axe run is a floor, not a result — the rest needs a keyboard and a human. Anyone selling automated compliance is selling the 30%.
2. Use the native element. <button>, <a href>, <input>, <select>,
<details> arrive with focusability, keyboard activation, correct role and
state announcement already handled. Almost every failure in the catalogue comes
from replacing one with a <div> and rebuilding a fraction of what was lost.
Its corollary is the first rule of ARIA: no ARIA beats bad ARIA, because
role="button" claims a contract a div does not fulfil.
What ships with it
7 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.
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.
- 1mo ago Changed · +29 lines · -66 tokens per session 79dc0aa7718a
- 1mo ago First seen · 206 lines · 197 tokens per session scan A 5ef087cbe7d7
a11y-ops is a skill published in the GitHub repository 0xDarkMatter/claude-mods (79 stars, last pushed 7d ago), licensed MIT. It adds 131 tokens to every session and 2,910 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-17.
a11y-ops compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| a11y-ops0xDarkMatter/claude-mods | Skill | 79 | 7d ago | MIT | A | 131 | Claude Code |
| brand-identitytravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 30 | Claude Code, Codex |
| ai-policy-generatortravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 42 | Claude Code, Codex |
| contract-redlinertravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 41 | Claude Code, Codex |
| legal-compliancetravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 49 | Claude Code, Codex |
| generic-react-ux-designertravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 69 | Claude Code, Codex |
| graphic-designtravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 32 | Claude Code, Codex |