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 rajitsaha/100xprism --skill a11y-auditorgit clone --depth 1 https://github.com/rajitsaha/100xprismWrote 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/rajitsaha/100xprism/a11y-auditor)<a href="https://agentmods.dev/skills/rajitsaha/100xprism/a11y-auditor"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/a11y-auditor/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.
<a href="https://agentmods.dev/skills/rajitsaha/100xprism/a11y-auditor"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/a11y-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 41 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium MCP Rug Pull · line 120 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 123 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 126 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00088 | $0.01869 |
| Opus 5 | $0.00044 | $0.00934 |
| Sonnet 5 | $0.00018 | $0.00374 |
| Haiku 4.5 | $0.00009 | $0.00187 |
Grade A, and why
a11y-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 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit the target against WCAG 2.2 Level AA plus pragmatic real-world a11y patterns. Report findings as actionable fixes, not academic citations.
Required Input
At least one of:
- URL or path to a built page
- Component source (HTML / JSX / Vue / Svelte)
- Design (Figma frame / screenshot) — restricts checks to visual-only
Optional context that sharpens the audit: target users (e.g. enterprise B2B, K-12, government — each implies different baselines), assistive tech in scope (VoiceOver, NVDA, JAWS, TalkBack, Switch Control), locale / RTL requirements, existing a11y posture (VPAT, prior audits, known waivers).
Audit Coverage
1. Perceivable
- Contrast — text ≥ 4.5:1 (body) / 3:1 (large/UI). Compute ratios; flag any below.
- Non-text content — every
<img>, icon, chart, decorative graphic has correctaltoraria-hidden. - Color independence — no information conveyed by color alone (errors, status, links).
- Text resize — usable up to 200% zoom without horizontal scroll at 1280px.
- Reflow — content reflows at 320 CSS px without loss of function.
2. Operable
- Keyboard parity — every interactive element reachable and operable via keyboard alone. No traps.
- Focus visible — visible focus ring on every focusable element, ≥ 3:1 against background.
- Focus order — DOM order matches visual order; tab through and map it.
- Target size — 24×24 CSS px minimum (WCAG 2.2 SC 2.5.8), 44×44 strongly preferred for touch.
- Skip links / landmarks —
<header>,<nav>,<main>,<footer>and skip-to-content link. - No motion traps — auto-play, parallax, looping animation respect
prefers-reduced-motion.
3. Understandable
- Language —
<html lang>set; switches declared withlangattribute. - Form labels — every input has a programmatic label (
<label for>,aria-label, oraria-labelledby). - Error identification — errors named in text, associated via
aria-describedby, announced to AT. - Predictable interaction — no context change on focus/input without warning.
- Consistent navigation — same nav patterns across pages.
What ships with it
1 file 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.
- 12d ago First seen · 148 lines · 88 tokens per session scan A eb27a1631d20
a11y-auditor is a skill published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 12d ago), licensed MIT. It adds 88 tokens to every session and 1,869 once invoked, about $0.0004 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.
Other skills, from other repositories
3d-web-experience
You bring the third dimension to the web. You know when 3D enhances and when it's just showing off. You balance visual impact with performance. You make 3D accessible to users who've never touched a 3D app. You create moments of wonder without sacrificing usability.
animation-engineer
Build smooth, accessible web animations using CSS, Framer Motion, and GSAP.
accessibility-champion
Professional Accessibility Champion Expert skill. Build accessible, performance-tuned, responsive UI components with clean design standards.
component-library
Professional Component Library Expert skill. Build accessible, performance-tuned, responsive UI components with clean design standards.
dark-mode-master
Professional Dark Mode Master skill. Build accessible, performance-tuned, responsive UI components with clean design standards.
data-table-builder
Professional Data Table Builder skill. Build accessible, performance-tuned, responsive UI components with clean design standards.