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 WrongStack/WrongStack --skill accessibilitygit clone --depth 1 https://github.com/WrongStack/WrongStackWrote 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/wrongstack/wrongstack/accessibility)<a href="https://agentmods.dev/skills/wrongstack/wrongstack/accessibility"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/accessibility/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/wrongstack/wrongstack/accessibility"><img src="https://agentmods.dev/badge/skills/wrongstack/wrongstack/accessibility.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 | $0.00051 | $0.00700 |
| Opus 5.5 | $0.00020 | $0.00280 |
| Sonnet 5.5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
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 10d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility
Selection card
- Task: Fix keyboard, focus and assistive technology behavior.
- Start: Identify the target surface, reference, user task and existing tokens.
- Finish: apply the acceptance checks below; report observed results and unresolved constraints.
Overview
Start from the actual user task and supported input modes. WCAG 2.2 is the current Recommendation used here; verify current standards when the required conformance target changes. A scanner score is not a conformance certificate.
Rules
- Prefer native controls and meaningful document structure. Use ARIA when it adds the semantics a custom widget actually needs, and keep values synchronized.
- Every action must work from a keyboard with visible, unobscured focus. Dialogs need sensible initial focus, dismissal and return focus.
- Give controls names, instructions and errors. Associate labels programmatically; placeholder text does not replace a label.
- Test real text and backgrounds for contrast: ordinary text 4.5:1, large text 3:1, applicable UI/graphics 3:1. Gradients and transparency need rendered values.
- WCAG 2.2 AA target size is 24 by 24 CSS pixels or a qualifying exception. 44 by 44 is a useful touch design target and the enhanced AAA criterion, not a universal AA requirement.
- Support zoom/reflow, reduced motion and forced colors as relevant. A drag action needs a single-pointer alternative; authentication should allow paste and password-manager assistance.
Workflow
- Identify route/state/viewport, task, affected shared primitives and conformance target. Inspect the actual rendered surface.
- Run the existing automated checker, then independently test keyboard, zoom/reflow, focus, errors and asynchronous updates.
- Use an available screen reader to check names, landmarks, reading order and announcements. If unavailable, record that gap instead of inventing evidence.
- Fix at the owning primitive where appropriate. Preserve the product's content and design intent while improving operation.
- Recheck the task and stress empty/error/loading states and long labels.
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.
- 10d ago Changed 205aeb4e4468
- 11d ago First seen · 71 lines · 51 tokens per session scan A f23bb581e63d
accessibility is a skill published in the GitHub repository WrongStack/WrongStack (388 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 700 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-10.
Other skills, from other repositories
readable-measure
Set line length and measure for comfortable reading across type sizes and breakpoints. Use when tuning body text. Covers measure only — for the full size and weight scale, use typography-scale.
von-restorff-effect
Apply the Von Restorff Effect — the element that differs from its neighbours is the one remembered. Use when a single action must dominate. For overall ordering rather than single-element emphasis, use visual-hierarchy.
handoff-spec
Write the implementation handoff — measurements, behaviours, assets, states, and edge cases. Use when engineering picks up the work. For verifying the result afterwards use design-qa-checklist; for reusable library components use component-spec (design-systems).
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
color-system
Build a product colour system — tonal scales, semantic roles, and contrast compliance. Use when defining or rebuilding colour from scratch. For dark-mode adaptation use dark-mode-design; for chart palettes use data-visualization; for multi-brand token architecture use theming-system (design-systems).
dark-mode-design
Adapt an existing palette to dark mode — surface elevation, contrast rebalancing, and desaturation rules. Use when you already have a light palette to translate. For building the base palette first, use color-system.