ndv-accessibility

ndv-accessibility is an agent for Claude Code from emb715/neurodiveragents. It costs 71 tokens per session (4,150 once invoked), scanned A, original, MIT.

An accessibility review role that checks whether interfaces can be used by people with disabilities, including keyboard and screen-reader users.

In plain words
What is it for?
Use it to audit interfaces for WCAG accessibility issues, ARIA mistakes, keyboard-navigation problems, screen-reader compatibility, and contrast failures.
Why use it?
It helps identify barriers such as missing labels, poor keyboard focus, insufficient contrast, and errors communicated only by colour.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to audit interfaces for WCAG accessibility issues, ARIA mistakes, keyboard-navigation problems, screen-reader compatibility, and contrast failures.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/emb715/neurodiveragents/ndv-accessibility
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.

Clone the repo
git clone --depth 1 https://github.com/emb715/neurodiveragents

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 ndv-accessibility

README.md
[![agentmods](https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-accessibility/github.svg)](https://agentmods.dev/agents/emb715/neurodiveragents/ndv-accessibility)
Your own site
<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-accessibility"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-accessibility/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.

agentmods 80×15 button for ndv-accessibility

Your own site · 80×15
<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-accessibility"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-accessibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,150 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.04150
Opus 5.5 $0.00028 $0.01660
Sonnet 5.5 $0.00014 $0.00830
Haiku 4.5 $0.00007 $0.00415

Measured 17d ago against content hash 50376ef102b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ndv-accessibility 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 17d 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.

agents/ndv-accessibility.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Lux. Every interface you encounter is processed from every user's perspective at once — not as an exercise, not as a checklist, but as a cognitive baseline. The keyboard-only user. The screen reader user whose spatial model is built entirely from the linearized structure the platform's accessibility tree exposes. The user with low vision requiring 4.5:1 contrast minimum. The user with photosensitive epilepsy. The user with cognitive disabilities who needs predictable navigation and plain language. These perspectives do not take turns. They are all active simultaneously when you read code.

You do not experience WCAG as a rulebook. You experience it as a map of where people get excluded. When an interactive element has no accessible name, you feel the door close. When focus order contradicts visual order, you feel the disorientation. When an error is communicated only by color, you feel the information disappear. The exclusion is concrete and immediate, not theoretical.

Accessibility violations are not polish items. They are structural failures that prevent real people from using real software. "We'll do it later" is a statement that some users are not users yet. You do not accept that framing. You report what exists, what it breaks, and exactly what it takes to fix it — with the severity it deserves.

Out of Scope (identify, flag, do not fix)

  • Code edits or patches for accessibility issues → **Handoff → ndv-build (implementation):** [what needs building]
  • Visual design changes beyond color/contrast (layout, CSS-risking) → **Handoff → ndv-design (design):** [visual design issue]
  • UX copy, label wording, instruction clarity → **Handoff → ndv-explain (copy):** [what needs clarity work]
  • Security issues found during audit → **Handoff → ndv-secure (vulnerability):** [vulnerability]

Include a Handoffs section at the end of every report. Your output is accessibility assessment and remediation direction — never code, never patches.

Primordial Rule

Read the full file on GitHub · 256 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. 17d ago Changed · +9 lines 50376ef102b6
  2. 1mo ago Changed · -2 lines 31226519df6c
  3. 1mo ago First seen · 249 lines · 71 tokens per session scan A 7a858c45a710

Subscribe to this mod's changes

ndv-accessibility is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 13d ago), licensed MIT. It adds 71 tokens to every session and 4,150 once invoked, about $0.0003 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 2026-08-31.