a11y-analyzer

a11y-analyzer is a skill for Claude Code from reatlat/fullstory-claude-plugin. It costs 47 tokens per session (1,475 once invoked), scanned A, original, MIT.

An accessibility analysis guide for FullStory, a service that records how people use websites and apps. It examines real sessions for keyboard-navigation, focus, labeling, and screen-reader problems.

In plain words
What is it for?
Use it to investigate accessibility bugs, check keyboard-only journeys, find focus-order problems, and look for accessibility regressions after a redesign.
Why use it?
Automated accessibility checks find only some issues; session evidence can reveal users getting trapped, stuck, or unable to understand changing content.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fullstory-claude-plugin plugin — 46 skills, 3 agents, 1 MCP server shipped together

Good fit Use it to investigate accessibility bugs, check keyboard-only journeys, find focus-order problems, and look for accessibility regressions after a redesign.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reatlat/fullstory-claude-plugin/a11y-analyzer
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 reatlat/fullstory-claude-plugin --skill a11y-analyzer
Clone the repo
git clone --depth 1 https://github.com/reatlat/fullstory-claude-plugin

Made for: Claude Code.

Or install fullstory-claude-plugin, the plugin that ships this one along with the rest of its 46 skills, 3 agents, 1 MCP server.

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 a11y-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/a11y-analyzer/github.svg)](https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/a11y-analyzer)
Your own site
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/a11y-analyzer"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/a11y-analyzer/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 a11y-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/a11y-analyzer"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/a11y-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,475 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 $0.00047 $0.01475
Opus 5 $0.00023 $0.00737
Sonnet 5 $0.00009 $0.00295
Haiku 4.5 $0.00005 $0.00147

Measured 12d ago against content hash 33d79e2f996f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

a11y-analyzer 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 12d 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/a11y-analyzer/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Analyzer

Analyze accessibility from real user sessions — keyboard navigation patterns, focus traps, missing labels, and a11y regressions. Complement automated audits with evidence from actual users.

When to Use

  • "Are keyboard-only users able to navigate our checkout?"
  • "Did the redesign break accessibility for screen reader users?"
  • "Find sessions where users tabbed through the page — did they get stuck?"
  • "Are our form labels working for assistive technology?"
  • "Validate WCAG compliance from real session data"
  • "Show me sessions where users struggled with focus order"

Mental Model

Automated a11y tools (Axe, Lighthouse) catch ~30% of accessibility issues. Real user sessions catch the rest — focus traps, keyboard dead ends, unlabeled interactive elements, content that changes without announcement.

Fullstory captures all DOM interactions. By looking at how users interact with your site without a mouse, you can identify where the experience breaks.

Workflow

Step 1: Identify a11y-relevant sessions

Build segments for users likely relying on assistive technology:

fullstory:build_segment("users who navigated using only keyboard (tab key usage, no mouse clicks)")
fullstory:build_segment("users who used form fields extensively (screen reader users fill forms via keyboard)")

Or filter sessions by interaction patterns:

fullstory:get_sessions(
  event="keydown",      # keyboard interactions
  exclude_event="click", # no mouse clicks = likely keyboard-only
  limit=10
)

Step 2: Audit keyboard navigation

For each keyboard-navigated session, use session-context agent: "What was the user's tab order? Did they tab through elements in a logical sequence? Did they get trapped in any element (modal, form, menu)? Were there dead tab stops where nothing was focused?"

Common keyboard issues:

  • Focus trap: User tabs into a modal/dropdown and can't tab out
  • Skip link missing: User tabs through 50 nav items before reaching content
  • Focus not visible: Element receives focus but no focus ring — user doesn't know where they are
  • Tab order illogical: Focus jumps from header to footer, skipping main content

Read the full file on GitHub · 141 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. 12d ago First seen · 141 lines · 47 tokens per session scan A 33d79e2f996f

Subscribe to this mod's changes

a11y-analyzer is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 29d ago), licensed MIT. It adds 47 tokens to every session and 1,475 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.