Borrowing it
Nothing to install: this file belongs to techtankto/techtank-site. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/techtankto/techtank-site/main/.agents/skills/accessibility/SKILL.mdgit clone --depth 1 https://github.com/techtankto/techtank-siteWrote 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/techtankto/techtank-site/accessibility)<a href="https://agentmods.dev/skills/techtankto/techtank-site/accessibility"><img src="https://agentmods.dev/badge/skills/techtankto/techtank-site/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/techtankto/techtank-site/accessibility"><img src="https://agentmods.dev/badge/skills/techtankto/techtank-site/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 | $0.00065 | $0.01823 |
| Opus 5.5 | $0.00026 | $0.00729 |
| Sonnet 5.5 | $0.00013 | $0.00365 |
| Haiku 4.5 | $0.00006 | $0.00182 |
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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility
The floor, not a cleanup pass. Appearance is the design contract's concern, where content lives is the data skill's, and component shape is the components skill's.
The baseline
- WCAG 2.0 AA is the legal floor, 2.2 AA is the target. AODA and the ACA both require AA. Cite the success criterion in every defect report and fix: the criterion decides whether a fix is sufficient.
- Automated checkers find the minority of it. WAVE, axe, and the IBM Equal Access checker catch missing names, contrast, and malformed ARIA. They miss focus order, a ring lost against its background, a card nobody can tab to, and motion that never stops. No route counts as audited without a keyboard-only pass and a screen reader pass.
- A third-party embed caps conformance at its own. An iframe's internals are not
reachable or restyleable from the host page. Name the ceiling, keep the parts you own
correct (an accurate
title, a reachable fallback), and record the defect against the vendor. Never report a vendor's defect as fixed, and never fake a fix around it.
Document structure
- One
mainper page. The persistent shell owns it and routes render sections inside it; a nested layout never renders its own. - Landmarks are semantic elements, not
divs with roles:header,nav,main,footer,section,article. Each landmark of a kind is named at the call site, never inside the component, because the name describes what that instance navigates: a site nav and a section sub-nav otherwise both announce as "navigation". - Heading levels never skip. An
h2followed by anh4is a defect on its own. - A list of title-and-description pairs is a description list.
dlwithdtandddmodels it exactly. Reach for it before inventing a heading level for a stepper, a glossary, or a spec table. - Disclosures use
detailsandsummary. The native element brings keyboard behaviour, state, and in-page find; a scripted accordion usually drops in-page find.
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.
- 1mo ago Changed · +107 lines · +5 tokens per session 95bb9b636498
- 2mo ago First seen · 15 lines · 60 tokens per session scan A a68ecc26599e
accessibility is a skill published in the GitHub repository techtankto/techtank-site (5 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 1,823 once invoked, about $0.0003 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 2026-08-31.
accessibility compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| accessibilitytechtankto/techtank-site | Skill | 5 | 3d ago | MIT | A | 65 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |