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.
npx skills add vadimcomanescu/codex-skills --skill accessibility-auditorgit clone --depth 1 https://github.com/vadimcomanescu/codex-skillsWrote 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.
[](https://agentmods.dev/skills/vadimcomanescu/codex-skills/accessibility-auditor)<a href="https://agentmods.dev/skills/vadimcomanescu/codex-skills/accessibility-auditor"><img src="https://agentmods.dev/badge/skills/vadimcomanescu/codex-skills/accessibility-auditor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00066 | $0.00508 |
| Opus 5 | $0.00033 | $0.00254 |
| Sonnet 5 | $0.00013 | $0.00102 |
| Haiku 4.5 | $0.00007 | $0.00051 |
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 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.
What it actually says
Accessibility Auditor
Make interfaces usable for everyone by finding and fixing WCAG issues with clear, actionable remediation.
Quick Start
- Scope the surface area (page(s), flow, or component set) and the target level (WCAG 2.1 AA by default).
- Audit in this order: structure → keyboard → contrast → forms → media → ARIA.
- Report issues as: Problem → Impact → Fix → Verification.
Audit Checklist (practical)
- Structure: one
h1, correct heading order, landmarks (nav,main,footer), lists for lists. - Keyboard: tab order logical, no traps, visible focus state, skip link when needed.
- Contrast: text ≥ 4.5:1 (AA), large text ≥ 3:1, UI elements ≥ 3:1.
- Forms: every input has a label; errors are announced and tied to fields.
- Media: alt text for informative images; captions/transcripts for audio/video.
- ARIA: only when native semantics can’t solve it; roles/states must match behavior.
Recommended Workflow
- Static review: check semantics in markup and component structure.
- Keyboard pass: navigate every interactive control without a mouse.
- Screen reader spot check: validate names, roles, and announcements.
- Contrast pass: verify text and UI component contrast ratios.
- Document fixes: include exact file/line (if codebase) and the change required.
Output Format (default)
- Summary: pass/fail and the highest-risk issues.
- Findings: numbered list with severity (High/Med/Low) and fix guidance.
- Verification steps: how to confirm each fix.
Guardrails
- Prefer native HTML semantics over ARIA.
- Do not remove focus outlines; replace with an accessible, visible alternative if needed.
- If a fix changes behavior, call out any product impact explicitly.
References
- Extended examples:
references/examples.md
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 43 lines · 66 tokens per session scan A 99740a6549df
accessibility-auditor is a skill published in the GitHub repository vadimcomanescu/codex-skills (24 stars, last pushed 7mo ago), licensed MIT. It adds 66 tokens to every session and 508 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 2026-08-30.
Other skills, from other repositories
accessibility-compliance-accessibility-audit
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance.
ss-review
Review UI code for design system compliance, accessibility, and best practices.
ada-plan-view-accessibility
Use when checking simplified ADA-derived plan-view bathroom accessibility constraints such as turning space, door clear width, toilet centerline, grab bars, and lavatory knee/toe clearance.
mqc-litigation-visual-redraw
Redraw a litigation diagram into a restrained, court-ready presentation graphic (SVG + PNG) WITHOUT changing any text or legal meaning. Use this whenever the user supplies a case timeline, a legal process flowchart, OR a party/relationship diagram and wants it cleaned up, beautified, redrawn, made professional…
patent-block-diagram
A workflow that turns a natural-language description into an editable `.pbd` patent block diagram, renders it in the diagram editor, checks the image, and exports a PNG.
form-accessibility
WCAG 2.2 AA compliance for forms, ARIA patterns, focus management, keyboard navigation, and screen reader support. Use when implementing accessible forms in any framework. The compliance foundation that ensures forms work for everyone.