accessibility-auditor

accessibility-auditor is a skill for Claude Code, Codex from lfyxhappy/lfcode. It costs 57 tokens per session (350 once invoked), scanned A, original, MIT.

An accessibility audit guide for checking whether a real web interface can be used with keyboards, assistive technology, different text sizes, and varied layouts. It examines the rendered page and its interaction states, not only source code.

In plain words
What is it for?
It helps inspect semantics, keyboard navigation, focus, dialogs, forms, error messages, contrast, zoom, narrow screens, and reduced-motion behavior.
Why use it?
It finds barriers that ordinary visual or automated checks can miss, such as missing labels, poor focus behavior, weak contrast, and unclear dynamic updates.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps inspect semantics, keyboard navigation, focus, dialogs, forms, error messages, contrast…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lfyxhappy/lfcode/accessibility-auditor
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.

Any agent
npx skills add lfyxhappy/lfcode --skill accessibility-auditor
Clone the repo
git clone --depth 1 https://github.com/lfyxhappy/lfcode

Made for: Claude Code, Codex.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/lfyxhappy/lfcode/accessibility-auditor.svg)](https://agentmods.dev/skills/lfyxhappy/lfcode/accessibility-auditor)
Your own site
<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/accessibility-auditor"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/accessibility-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 350 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 $0.00057 $0.00350
Opus 5 $0.00028 $0.00175
Sonnet 5 $0.00011 $0.00070
Haiku 4.5 $0.00006 $0.00035

Measured yesterday against content hash e62634cb0b67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

accessibility-auditor 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 yesterday.

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.

packages/lfcode/src/skill/lfcode/.bundle/accessibility-auditor/SKILL.md · 28 lines

What it actually says

Accessibility Auditor

Evaluate usable access across semantics, interaction, visual presentation, and dynamic updates.

Workflow

  1. Identify the target route, supported platforms, user flows, viewport sizes, component states, and applicable accessibility standard or product requirement.
  2. Inspect the real DOM and rendered UI, not only source JSX or templates. Check landmarks, headings, labels, roles, names, descriptions, form errors, live regions, and table or dialog structure.
  3. Exercise keyboard-only navigation, focus visibility and order, pointer alternatives, escape and submit behavior, loading and error updates, zoom or narrow layouts, and reduced-motion behavior where applicable.
  4. Check color contrast, text scaling, overflow, hit targets, non-text alternatives, and status messages with available local tools. Record reproducible steps and exact elements.
  5. Classify findings by user impact and confidence. Suggest the smallest remediation without changing product semantics; implement only when authorized.
  6. Re-run the same flows after a fix and inspect browser console, page errors, and relevant automated checks.

Boundaries

  • Do not claim full compliance from a limited automated scan or a single browser and viewport.
  • Do not remove content, alter focus management, or weaken semantics to silence a checker.
  • Redact user data from screenshots and accessibility trees when sharing evidence.

Completion check

Report finding, affected state, reproduction, expected behavior, severity rationale, verification, and coverage gaps.

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. yesterday First seen · 28 lines · 57 tokens per session scan A e62634cb0b67

Subscribe to this mod's changes

accessibility-auditor is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 350 once invoked, about $0.0003 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 2026-09-05.

Related

Other skills, from other repositories

design-taste-frontend

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

dmae97/omk · 61 tokens

design-taste-frontend-v1

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

dmae97/omk · 61 tokens

high-end-visual-design

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

dmae97/omk · 53 tokens

gpt-taste

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

dmae97/omk · 72 tokens

frontend-design

Production-grade UI/UX guidance — not generic AI slop. Triggers on design, UI, frontend, component, styling, layout, make it look good.

AyushParkara/syntra · 36 tokens

frontend-craft-director

A self-contained frontend design, redesign, audit, implementation, anti-AI-slop, and rendered visual-QA skill for use directly inside a ChatGPT conversation or through a local MCP-accessible project.

mehrdad03/localdev-mcp · 47 tokens