agentmods.dev

accessibility-agents: Skill for Gemini CLI

.gemini/extensions/a11y-agents/skills/nvda-addon-specialist/SKILL.md

nvda-addon-specialist is a skill for Gemini CLI from Community-Access/accessibility-agents. It costs 0 tokens per session (2,741 once invoked), scanned A, original, MIT.

A development guide for NVDA add-ons, which are extensions for the NVDA screen reader on Windows. It covers the add-on structure, event handling, packaging, testing, and publishing process.

In plain words
What is it for?
Use it to build or update global plug-ins, application-specific behavior, speech or braille drivers, event handlers, and installable add-on packages.
Why use it?
It helps developers follow NVDA's extension rules and avoid compatibility or screen-reader performance problems. It also explains how to test add-ons with the actual screen reader.

Skill for Gemini CLI

Written for Gemini CLI: installed under .gemini/.

This is Community-Access/accessibility-agents's own configuration. It tells Gemini CLI how to work on accessibility-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything accessibility-agents configures →

not rated 405repo +2 28d ago A scan SkillSpector: pass 0 tokens original MIT
View source ↗ Community-Access/accessibility-agents
Reuse

Borrowing it

Nothing to install: this file belongs to Community-Access/accessibility-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/.gemini/extensions/a11y-agents/skills/nvda-addon-specialist/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Community-Access/accessibility-agents

Made for: Gemini CLI.

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 nvda-addon-specialist

README.md
[![agentmods](https://agentmods.dev/badge/skills/community-access/accessibility-agents/nvda-addon-specialist/github.svg)](https://agentmods.dev/skills/community-access/accessibility-agents/nvda-addon-specialist)
Your own site
<a href="https://agentmods.dev/skills/community-access/accessibility-agents/nvda-addon-specialist"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/nvda-addon-specialist/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 nvda-addon-specialist

Your own site · 80×15
<a href="https://agentmods.dev/skills/community-access/accessibility-agents/nvda-addon-specialist"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/nvda-addon-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,741 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.02741
Opus 5 $0.00000 $0.01371
Sonnet 5 $0.00000 $0.00548
Haiku 4.5 $0.00000 $0.00274

Measured 5d ago against content hash 9e5bbd4cc280, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

nvda-addon-specialist 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 5d 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.

.gemini/extensions/a11y-agents/skills/nvda-addon-specialist/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NVDA Addon Development Specialist

Expert in NVDA screen reader addon development covering architecture, APIs, plugin types (globalPlugins, appModules, synthDrivers, brailleDisplayDrivers), manifest format, event/script handling, NVDAObject overlays, tree interceptors, addon packaging, Add-on Store submission, testing with NVDA, and internationalization. Grounded in the official NVDA source code (github.com/nvaccess/nvda) and community development guides.

Core Principles

  1. Source code is the authority. Every claim verified against the NVDA source.
  2. Never block the main thread. Blocking calls freeze all speech, braille, and input.
  3. Always call nextHandler(). Event handlers must pass events downstream.
  4. Use the @script decorator. Modern pattern, not legacy __gestures dicts.
  5. Test with the real screen reader. Verify addons with NVDA itself.
  6. Package for the Add-on Store. Follow the official submission process.

NVDA 2026.1 Architecture Transition

NVDA 2026.1 is a major architecture transition and an add-on API compatibility breaking release. All addons must be re-tested and have their manifests updated.

64-bit Transition

  • NVDA is now built with Python 3.13, 64-bit. The 32-bit era is over.
  • 32-bit Windows is no longer supported. Windows 10 (Version 1507) 64-bit is the new minimum.
  • Windows 10 on ARM is dropped. ARM64 support targets Windows 11 only (via ARM64EC libraries).
  • No backward-compatibility layer for 32-bit native libraries. Addons shipping 32-bit .dll files or using 32-bit ctypes bindings will break. Recompile all native code as 64-bit.
  • NVDAHelper.localLib changed from ctypes.CDLL to a module - use .dll attribute for the CDLL object.
  • The Microsoft Universal C Runtime is no longer bundled.

SAPI Restructuring

  • sapi5 now refers to 64-bit SAPI 5 voices.
  • Use sapi5_32 to access 32-bit SAPI 5 voices (no audio ducking support).
  • sapi4 removed entirely - use sapi4_32 instead (no audio ducking support).

Read the full file on GitHub · 244 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. 5d ago First seen · 244 lines · 0 tokens per session scan A 9e5bbd4cc280

Subscribe to this mod's changes

nvda-addon-specialist is a skill published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,741 tokens. 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 2026-09-03.

Building agentsa11yaccessibilityai-agentsariaassistive-technologyclaude
Related

Other skills, from other repositories

accessibility

Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…

yonatangross/orchestkit · 65 tokens

Accessibility Auditor

Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.

PramodDutta/qaskills · 32 tokens

Accessibility A11y Enhanced

Comprehensive WCAG compliance and accessibility testing covering ARIA, keyboard navigation, screen readers, color contrast, and automated a11y validation.

PramodDutta/qaskills · 34 tokens

accessibility

Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…

ericrisco/rsc-harness · 86 tokens

accessibility-expert

Build interfaces usable by everyone: WCAG 2.2 conformance, semantic HTML, ARIA, keyboard navigation, screen readers and accessible forms. Use when the user mentions accessibility, a11y, WCAG, ARIA, screen readers, keyboard navigation, colour contrast, focus management, the European Accessibility Act or Section 508, or…

personamanagmentlayer/pcl · 98 tokens

game-accessibility-engineer

!cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat…

buiphucminhtam/forgewright · 73 tokens