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 Eliyce/paqad-ai --skill accessibility-reviewgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/accessibility-review)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/accessibility-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/accessibility-review/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/eliyce/paqad-ai/accessibility-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/accessibility-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.00991 |
| Opus 5 | $0.00025 | $0.00495 |
| Sonnet 5 | $0.00010 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
accessibility-review 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 9d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Audits the UI against WCAG 2.2 A/AA. Combines (1) static scan for missing ARIA, missing alt text, and obvious focus issues with (2) axe-core results from the Playwright walk (Step 3 of the workflow). Every finding cites a WCAG 2.2 success criterion id — the design-test analog of WSTG ids in pentest.
Use This When
Use this for every design-test run. Driven by the live phase's axe-core output when available; static-only when the live phase is blocked.
Inputs
- Read
docs/instructions/design-system/accessibility.mdfor declared a11y rules. - Read
references/wcag-mapping.mdto map findings to WCAG ids. - Read the axe-core results JSON from
runtime-checks.tsif the live phase ran.
Procedure
Detection and mapping are deterministic — the LLM picks severity and writes findings; the scripts do the spotting.
- Static scan: run
scripts/static-a11y-scan.sh [search-root]→ TSV of<category>\t<file>:<line>\t<excerpt>. Categories:img-no-alt | button-no-name | anchor-no-name | input-no-label | outline-zero | positive-tabindex | missing-lang. - Live axe results: when the Step 3 runtime walk produced an axe JSON, run
scripts/parse-axe-violations.sh <axe-results.json>→ TSV of<route>\t<rule-id>\t<impact>\t<target>\t<help>. Accepts either a full runtime-checks payload or a bare violations array. - For each axe rule emitted, run
scripts/map-axe-to-wcag.sh <rule-id>to get its primary WCAG 2.2 success criterion id. Unmapped rules returnWCAG-UNKNOWN; map those manually using the published axe docs. - Verify each rule declared in
accessibility.md: contrast ratio met, focus ring visible, target size ≥ declared minimum, reduced-motion respected, keyboard order matches reading order. - Cross-reference with
tokens.md— contrast violations point at the token pair that's failing (e.g.color.text.mutedoncolor.surface.base= 3.8:1, below 4.5:1).
Output Contract
- Match
assets/output.template.md.contract_refis a WCAG id likeWCAG-2.2-1.4.3(contrast) or the relevantaccessibility.mdclause. - Default severity: WCAG Level A violations → blocker, Level AA → high, design-system-specific rules → medium.
- Output must pass
scripts/lint-findings.sh(exit 0).
What ships with it
7 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.
- 9d ago First seen · 75 lines · 50 tokens per session scan A 9647f2e2d4db
accessibility-review is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 991 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 2026-09-03.
Other skills, from other repositories
make-interfaces-feel-better
Use when building or reviewing UI polish: typography, hit areas, nested radius, optical alignment, shadows, media outlines, micro-interactions, and animation performance.
frontend-skill
Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Use whenever the task produces or modifies anything a user will see rendered — websites, landing pages, web apps, dashboards, React/HTML/Vue components, artifacts with visual output, style overhauls, or "make this…
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.