accessibility

accessibility is a skill for Claude Code, Codex from VeryGoodOpenSource/vgv-ai-flutter-plugin. It costs 42 tokens per session (5,309 once invoked), scanned A, original, MIT.

A Flutter accessibility reviewer for checking app interfaces against WCAG 2.2, a set of guidelines for making software usable by people with disabilities. It covers mobile, web, and desktop platforms.

In plain words
What is it for?
Use it to audit or improve semantics, touch targets, keyboard focus, colour contrast, text scaling, motion, and platform-specific accessibility behaviour.
Why use it?
It helps find accessibility problems in Flutter widgets and guides fixes so people can use the app with different assistive technologies, input methods, text sizes, and motion preferences.

Skill for Claude CodeCodex

Part of the vgv-ai-flutter-plugin plugin — 15 skills, 1 agent, 3 hooks, 2 MCP servers shipped together

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 skills/verygoodopensource/vgv-ai-flutter-plugin/accessibility
Any agent
npx skills add VeryGoodOpenSource/vgv-ai-flutter-plugin --skill accessibility
Clone the repo
git clone --depth 1 https://github.com/VeryGoodOpenSource/vgv-ai-flutter-plugin

Made for: Claude Code, Codex.

Or install vgv-ai-flutter-plugin, the plugin that ships this one along with the rest of its 15 skills, 1 agent, 3 hooks, 2 MCP servers.

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 accessibility

README.md
[![agentmods](https://agentmods.dev/badge/skills/verygoodopensource/vgv-ai-flutter-plugin/accessibility.svg)](https://agentmods.dev/skills/verygoodopensource/vgv-ai-flutter-plugin/accessibility)
Your own site
<a href="https://agentmods.dev/skills/verygoodopensource/vgv-ai-flutter-plugin/accessibility"><img src="https://agentmods.dev/badge/skills/verygoodopensource/vgv-ai-flutter-plugin/accessibility.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,309 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 $0.00042 $0.05309
Opus 5 $0.00021 $0.02655
Sonnet 5 $0.00008 $0.01062
Haiku 4.5 $0.00004 $0.00531

Measured 3d ago against content hash 72d7dbbe4c55, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

skills/accessibility/SKILL.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility

Flutter accessibility auditing and remediation across WCAG 2.2 conformance levels A, AA, and AAA. The skill is split into a workflow (this file) plus reference files loaded on demand:

  • references/audit-templates.md — severity guide, report template, level-specific passed-check lists for A, AA, AA + selected AAA, and AAA. Also includes cross-platform severity adjustment table.
  • references/examples.md — extended Flutter code per category, including WCAG 2.2 patterns (focus-not-obscured, dragging alternatives, Cupertino semantic wrappers, MergeSemantics correctness).
  • references/widget-mapping.md — table mapping each Flutter widget to its accessibility requirement and the recommended implementation. Use it when auditing a specific widget.
  • references/testing.md — complete accessibility test suite covering semantics, touch targets, focus management, contrast, text scaling, and motion. Use it when writing the tests that lock in a remediation.
  • references/platforms/ios.md, android.md, web.md, macos.md, windows.md, linux.md — per-platform WCAG 2.2 checks. Load only the file(s) matching the selected platform(s).

Read whichever reference file matches the current phase. Do not duplicate its content here.


Core Standards

Apply these standards to all accessibility work:

Conformance Level — Begin every audit by asking which WCAG 2.2 conformance level the project targets (A, AA, AA + selected AAA, or AAA). Never assume AA.

Platform Selection — Begin every audit by asking which of the six platforms are targeted (iOS, Android, Web, macOS, Windows, Linux). Apply the platform rules from the matching file(s) in references/platforms/.

Read the full file on GitHub · 319 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. 3d ago First seen · 319 lines · 42 tokens per session scan A 72d7dbbe4c55

Subscribe to this mod's changes

accessibility is a skill published in the GitHub repository VeryGoodOpenSource/vgv-ai-flutter-plugin (157 stars, last pushed 14d ago), licensed MIT. It adds 42 tokens to every session and 5,309 once invoked, about $0.0002 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 2026-08-30.