A read-only accessibility check for user-facing Flutter screens. Accessibility means making an interface usable with screen readers, larger text, keyboard or touch input, and different vision needs.

Run it before shipping a screen or after layout changes to review semantics, contrast, touch sizes, text scaling, focus flow, and reduced-motion support.

It finds issues that a general code review may miss, such as missing labels, weak color contrast, small touch targets, incorrect focus order, and motion that cannot be disabled.

check-a11y — Command for Claude Code by obiwancenobi

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/obiwancenobi/klamben

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/obiwancenobi/klamben/check-a11y/github.svg)](https://agentmods.dev/commands/obiwancenobi/klamben/check-a11y)

Your own site

<a href="https://agentmods.dev/commands/obiwancenobi/klamben/check-a11y"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/check-a11y/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/obiwancenobi/klamben/check-a11y"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/check-a11y.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 525 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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.00525
Opus 5	$0.00013	$0.00262
Sonnet 5	$0.00005	$0.00105
Haiku 4.5	$0.00003	$0.00052

Measured 10d ago against content hash e803d5922db3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

check-a11y 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 10d 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.

src/commands/check-a11y.md · 63 lines

What it actually says

Accessibility-focused audit. Catches what /audit doesn't always surface.

When to use

Before shipping any user-facing screen
After a layout change
User asks "is this accessible" / "check a11y"

Checks

Check design context: If .klamben.md exists in the project root, read it first. Apply the project's brand, platform targets, accessibility tier, and existing patterns to your work below.
Semantic labels — IconButton without tooltip, Image.asset without Semantics label, tappable Container without accessible name
Touch targets — Interactive elements <48dp/44pt
Contrast — Text color vs background (flag obvious fails: Colors.grey on Colors.white, custom pairs)
Focus order — Form fields in visual order, no trapped focus
Scaled text — Text that would overflow at textScaleFactor = 2.0
Reduced motion — Animations that ignore MediaQuery.disableAnimations
Screen reader labels — Semantics exclusion on decorative images, label on meaningful ones

Output format

A11y check for lib/screens/settings.dart

CRITICAL (2)
  11:7  IconButton(Icons.close) missing tooltip
  24:15 Icon(Icons.warning) standalone — no accessible name

WARNING (3)
  33:8  Tap target 32×32 on reminder toggle — needs ≥48dp
  47:11 Text('Reminder') on Color(0xFFCCCCCC) bg — 2.8:1 (needs 4.5:1)
  62:4  Text widget will overflow Row at textScaleFactor=2.0

OK
- Form fields in visual order
- No trapped focus
- Navigation respects reduced motion

5 issues (2 critical, 3 warning).

Do NOT

Fix the issues automatically — this is read-only
Suggest rewriting unrelated code
Skip silent issues (tooltip absence is silent but critical)

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.

10d ago First seen · 63 lines · 26 tokens per session scan A e803d5922db3

Subscribe to this mod's changes

check-a11y is a command published in the GitHub repository obiwancenobi/klamben (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 525 once invoked, about $0.0001 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.

Design and UX Frontend agent-skills ai ai-harness design-skills flutter slash-command

seed-create-component

A command for creating a new SEED Design component, including its source specification, recipes, React implementation, documentation, examples, and optional headless layer.

daangn/seed-design · 12 tokens

sddesign

Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes .ui-craft/spec.md. Run when starting a net-new surface from scratch.

educlopez/ui-craft · 46 tokens

craft

One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface ("build me a dashboard", "I need a landing page") and expects a shippable result, not component-level help.

educlopez/ui-craft · 64 tokens

check-a11y