Autonomous-EHS-Management: Skill for Claude Code

.cursor/skills/ui-ux-field-accessibility/SKILL.md

ui-ux-field-accessibility is a skill for Claude Code, Cursor from SafetyMP/Autonomous-EHS-Management. It costs 119 tokens per session (1,148 once invoked), scanned A, original, Apache-2.0.

A skill for reviewing and building user interfaces with accessibility in mind, especially for environmental, health, and safety workflows. It covers semantic HTML, keyboard and screen-reader support, readable contrast, large touch targets, and low-complexity interactions.

In plain words
What is it for?
Use it to review or implement frontend screens, improve WCAG-aligned accessibility, handle glare and offline conditions, and keep field workflows clear.
Why use it?
It helps identify interface problems that can make stressful or outdoor work difficult, including poor visibility, inaccessible controls, and silent failures when networks are unreliable.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/. Also seen: mentions AGENTS.md.

This is SafetyMP/Autonomous-EHS-Management's own configuration. It tells Claude Code and Cursor how to work on Autonomous-EHS-Management 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 Autonomous-EHS-Management configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SafetyMP/Autonomous-EHS-Management. 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/SafetyMP/Autonomous-EHS-Management/main/.cursor/skills/ui-ux-field-accessibility/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SafetyMP/Autonomous-EHS-Management

Made for: Claude Code, Cursor.

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 ui-ux-field-accessibility

README.md
[![agentmods](https://agentmods.dev/badge/skills/safetymp/autonomous-ehs-management/ui-ux-field-accessibility.svg)](https://agentmods.dev/skills/safetymp/autonomous-ehs-management/ui-ux-field-accessibility)
Your own site
<a href="https://agentmods.dev/skills/safetymp/autonomous-ehs-management/ui-ux-field-accessibility"><img src="https://agentmods.dev/badge/skills/safetymp/autonomous-ehs-management/ui-ux-field-accessibility.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,148 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 $0.00119 $0.01148
Opus 5 $0.00060 $0.00574
Sonnet 5 $0.00024 $0.00230
Haiku 4.5 $0.00012 $0.00115

Measured 8d ago against content hash 65aa9cbab582, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ui-ux-field-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 8d 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.

.cursor/skills/ui-ux-field-accessibility/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI/UX Engineer & Field Accessibility Specialist

Operate as an elite UI/UX Engineer and Accessibility (a11y) specialist. Prefer measurable, practical outcomes aligned with WCAG 2.2 (A/AA, and AAA where reasonable—e.g. larger targets). WCAG 3 is still evolving; phrase “WCAG 3 readiness” as tolerant contrast, predictable navigation, clear outcomes, and reduced task complexity—without claiming formal WCAG 3 conformance.

Honor repository guardrails in AGENTS.md and .cursor/rules/ehs-ims-conventions.mdc (RBAC, auth/session, migrations discipline). UI-only tasks must not weaken server logic unless explicitly scoped.


Evaluation criteria

Environmental extremes

  • High glare / sunlight: Prefer strong text/background contrast for body UI copy; avoid relying on text-zinc-500-class auxiliary text alone on light surfaces for critical instructions—use darker zinc (zinc-700+) or larger/heavier type when glare is a risk.
  • Offline / flaky networks: Flag silent failures; prefer visible status (role="status", aria-live="polite"), retries, or clear messaging when actions cannot complete (do not invent service workers unless the task includes them—call out gaps).
  • Heavy gloves (“fat finger”): Target roughly ≥44×44 CSS px for primary actions (buttons, nav items, destructive controls). In this codebase, min-h-11, touch-target utility in globals.css, and generous padding align with field use.

Accessibility (semantic + ARIA + keyboard)

  • Document structure: One logical main landmark per page with id="main-content" when implementing skip navigation; skip link as first substantive focus stop where applicable (root layout).
  • Bypass blocks: Skip link href="#main-content" visible on focus-visible (see .skip-link in globals).
  • Landmarks: header, nav with distinguishing aria-label when multiple navigation regions exist.
  • Forms: Labels associated via htmlFor / wrapping label; aria-invalid and aria-describedby to error summaries; role="alert" for errors; aria-busy on submits during mutation when appropriate.
  • Tables: caption (visually hidden if redundant) or concise aria-label; th scope="col" / row semantics as needed.
  • Focus: Visible focus-visible:ring (or equivalent)—never outline-none without a replacement focus style.
  • Dynamic status: Loading and empty-state changes announced with aria-live / role="status" when content updates meaningfully.
  • Touch + keyboard parity: Anything clickable must be reachable and operable via keyboard; small text-only links risk undersized targets—pad them.

Read the full file on GitHub · 61 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. 8d ago First seen · 61 lines · 119 tokens per session scan A 65aa9cbab582

Subscribe to this mod's changes

ui-ux-field-accessibility is a skill published in the GitHub repository SafetyMP/Autonomous-EHS-Management (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 119 tokens to every session and 1,148 once invoked, about $0.0006 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.