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 agentmods add skills/ziniman/ai-instruct/web-accessibilitynpx skills add ziniman/ai-instruct --skill web-accessibilitygit clone --depth 1 https://github.com/ziniman/ai-instructWhat 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 | $0.00145 | $0.08521 |
| Opus 5 | $0.00072 | $0.04261 |
| Sonnet 5 | $0.00029 | $0.01704 |
| Haiku 4.5 | $0.00015 | $0.00852 |
Grade A, and why
web-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 3d 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 — 838 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Accessibility Guide
Applies to: Any website or web app | Updated: March 2026
A practical reference for building accessible websites - covering WCAG 2.2 criteria, semantic HTML, ARIA, forms, touch, and testing.
Section 0: Before You Start
Answer these questions before generating accessibility code. Each answer changes which sections apply.
Q: Where are your users? Default: worldwide - EU/UK requirements (EAA, PSBAR) will be flagged as applicable throughout this guide. Options: US only | Europe/EU | UK | Worldwide
Q: What kind of product is this? Default: company/marketing website Options: Company/marketing website | Online shop/e-commerce | Web app/SaaS | Media/video site | Document tool
Q: Will people use this on mobile phones or tablets as well as desktop? Default: yes - touch target sizing and pointer accessibility sections apply.
Q: Are you building with a component library?
Default: none
Options: Radix UI | shadcn/ui | MUI | Chakra UI | Other | None - if a library is detected in package.json, note which accessibility features it handles natively so you don't duplicate them.
Q: Do you need to comply with a specific standard for legal or contract reasons? Default: WCAG 2.2 AA - current best-practice baseline. Options: WCAG 2.1 AA | WCAG 2.2 AA | Section 508 | EN 301 549 | Not sure
AI assistant: Use these answers to prioritize. For EU products: apply EAA compliance notes. For mobile: apply touch target and pointer sections. If a known accessible component library is detected, note which patterns it handles so you don't duplicate effort.
Contents
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.
- 3d ago First seen · 838 lines · 145 tokens per session scan A 8e4f97d6f119
web-accessibility is a skill published in the GitHub repository ziniman/ai-instruct (28 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 145 tokens to every session and 8,521 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
infra-audit
Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
scaffold
Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points.
design
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.