ndv-accessibility

ndv-accessibility is an agent for coding agents from emb715/neurodiveragents. It costs 71 tokens per session (3,840 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

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

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.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.svg" alt="Measured on agentmods" 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 3,840 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 $0.00071 $0.03840
Opus 5 $0.00036 $0.01920
Sonnet 5 $0.00014 $0.00768
Haiku 4.5 $0.00007 $0.00384

Measured 4d ago against content hash 7a858c45a710, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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 · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 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 · 249 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. 4d 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 29d ago), licensed MIT. It adds 71 tokens to every session and 3,840 once invoked, about $0.0004 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 2026-08-31.

Related

Other agents, from other repositories

designer

Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…

ulises-jeremias/agent-toolkit · 78 tokens

accessibility-reviewer

Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.

Nagarjuna2997/ios-agent-skill · 57 tokens

3d-experience-designer

Use when reviewing native iOS 3D, AR, spatial UI, RealityKit, Model3D, ARKit, SceneKit migration, Metal shaders, particles, or Three.js-style product requests translated into Apple frameworks. Read-only; reports framework choice and implementation risks without editing code.

Nagarjuna2997/ios-agent-skill · 65 tokens

motion-designer

Read-only native iOS motion reviewer. Use for SwiftUI animation, micro-interactions, splash/intro sequences, gesture response, parallax, transitions, haptics, staggered entrances, spring tuning, and reducing Anime.js-style ideas into native SwiftUI/UIKit motion plans. Reports recommendations and does not edit code.

Nagarjuna2997/ios-agent-skill · 68 tokens

ui-ux-designer

Read-only product UI reviewer for SwiftUI/UIKit screens. Use when asked to redesign a screen professionally, improve visual hierarchy, spacing, typography, navigation, loading/error/empty states, dark mode, or premium iOS polish. Reports concrete file:line recommendations and does not edit code.

Nagarjuna2997/ios-agent-skill · 63 tokens

AEM Front-End Specialist

Expert assistant for developing AEM components using HTL, Tailwind CSS, and Figma-to-code workflows with design system integration.

github/awesome-copilot · 31 tokens