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 sigistry/marketplace --skill wcag-remediationgit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/sigistry/marketplace/wcag-remediation)<a href="https://agentmods.dev/skills/sigistry/marketplace/wcag-remediation"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/wcag-remediation/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/sigistry/marketplace/wcag-remediation"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/wcag-remediation.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 | $0.00096 | $0.00969 |
| Opus 5 | $0.00048 | $0.00485 |
| Sonnet 5 | $0.00019 | $0.00194 |
| Haiku 4.5 | $0.00010 | $0.00097 |
Grade A, and why
wcag-remediation 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WCAG Remediation
Purpose
Provide a standardized, static methodology for fixing accessibility failures, not just detecting them. Automated scanners are structurally limited: axe-core catches roughly a third to a half of WCAG issues, and linters like jsx-a11y reason about one element at a time, so they are blind to relationships (a control and its label in different subtrees), to behavior over time (focus when a dialog opens/closes), and to whether a chosen ARIA pattern is complete. This skill encodes the fixes that require reading the whole component.
The Remediation Order of Operations
Apply fixes in this priority, a lower step often removes the need for a higher one:
- Use the right native element. A
<button>,<a href>,<label>,<input>,<dialog>, or<nav>brings a role, keyboard behavior, and focusability for free. Replacing a<div onClick>with a<button>fixes 2.1.1, 2.4.7, and 4.1.2 in one edit. - Establish relationships. Associate inputs with
<label for>; name controls with visible text viaaria-labelledbybefore inventing anaria-label; group with<fieldset>/<legend>. - Add ARIA only where native falls short, and add the complete pattern, all required roles, states, and keyboard interactions from the APG, never a lone
role. - Fix focus behavior: trap, move-in, restore, background inertness, visible focus.
- Fix perceivability: contrast, text alternatives, heading/landmark structure.
The First Rule of ARIA
No ARIA is better than bad ARIA. Prefer removing incorrect ARIA over adding more. A redundant role="button" on a <button>, an aria-label that overrides good visible text, or aria-hidden="true" on a focusable element are each worse than nothing.
Cross-Element Fixes Linters Miss
| Failure | Why linters miss it | The fix | WCAG SC |
|---|---|---|---|
| Icon button, no name | Element is valid in isolation | aria-labelledby to nearby text, else aria-label |
1.1.1, 4.1.2 |
| Input labeled by distant text | Label lives in another subtree | aria-labelledby / <label for> |
1.3.1, 3.3.2 |
| Custom widget missing state | State belongs on a different element | aria-expanded/aria-selected/aria-checked on the right node |
4.1.2 |
| Focus lost on dialog close | It is a runtime behavior, not an attribute | store & restore the trigger element | 2.4.3 |
| Contrast fails against a token | Colors resolve through the theme | remap to nearest passing design token | 1.4.3, 1.4.11 |
| Reading order ≠ DOM order | Requires understanding layout intent | reorder DOM or fix tabindex/order |
1.3.2, 2.4.3 |
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.
- 12d ago First seen · 41 lines · 96 tokens per session scan A 1fdc832597ba
wcag-remediation is a skill published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 969 once invoked, about $0.0005 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
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
design-sprint
Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate before we build", "rapid prototype", "test with users", or "should we build this". Also trigger when a team is stuck in endless debate over a high-stakes product…
steve-jobs-design-review
Review designs, products, and features with Steve Jobs' standards: ruthless simplicity, focus, and end-to-end excellence. Use when the user mentions "Steve Jobs review", "design review", "product review", "what would Steve do", "insanely great", "this feels too complicated", "too many features", "product taste"…
web-typography
Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", "typographic scale", or "the text is hard to read". Also trigger when choosing between system…
hooked-ux
Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users arent coming back", "habit formation", "engagement loops", "habit zone", or "the manipulation matrix". Also trigger when designing notification or re-engagement strategies, building…