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/danielpodolsky/ownyourcode/accessibilitynpx skills add DanielPodolsky/ownyourcode --skill accessibilitygit clone --depth 1 https://github.com/DanielPodolsky/ownyourcodeWhat 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 | $0.00049 | $0.01836 |
| Opus 5 | $0.00024 | $0.00918 |
| Sonnet 5 | $0.00010 | $0.00367 |
| Haiku 4.5 | $0.00005 | $0.00184 |
Grade A, and why
accessibility-fundamentals 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 2d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Fundamentals Review
"Accessibility is not a feature, it's a requirement. If 15% of users can't use your app, you've failed 15% of users."
When to Apply
Activate this skill when:
- Reviewing JSX with buttons, links, or forms
- Seeing custom interactive components
- Forms with inputs and labels
- Navigation menus
- Modal dialogs
- Any user interaction code
The Accessibility Checklist
Must Have (Every Interactive Element)
- Keyboard accessible — All actions work with Tab + Enter/Space
- Focus visible — Clear visual indicator of focused element
- Semantic elements —
<button>not<div onClick> - Form labels — Every input has an associated
<label> - Alt text — Images have descriptive alt attributes
- Sufficient contrast — Text readable against background (4.5:1 ratio)
Should Have (Complex Interactions)
- ARIA labels — Icon-only buttons have
aria-label - Focus trapping — Modals trap focus until closed
- Skip links — "Skip to main content" for keyboard users
- Live regions — Dynamic content announced to screen readers
- Error messages — Linked to inputs with
aria-describedby
Never Do
- Rely on color alone — Color should not be the only indicator
- Remove focus outlines — Never
outline: nonewithout replacement - Use divs for buttons — Use semantic
<button>or<a> - Trap users — Always provide escape from modals/menus
Common Mistakes (Anti-Patterns)
1. Div as Button
// ❌ BAD: Not keyboard accessible, no semantics
<div onClick={handleClick} className="button">
Click me
</div>
// ✅ GOOD: Native button element
<button onClick={handleClick} className="button">
Click me
</button>
Why it matters: <div onClick> doesn't receive keyboard focus, doesn't respond to Enter/Space, and isn't announced as a button by screen readers.
2. Missing Form Labels
// ❌ BAD: Input has no label
<input type="email" placeholder="Email" />
// ✅ GOOD: Label linked to input
<label htmlFor="email">Email</label>
<input id="email" type="email" placeholder="[email protected]" />
// ✅ ALSO GOOD: Wrapping label
<label>
Email
<input type="email" />
</label>
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.
- 2d ago First seen · 287 lines · 49 tokens per session scan A 9ca5a8973e62
accessibility-fundamentals is a skill published in the GitHub repository DanielPodolsky/ownyourcode (276 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,836 once invoked, about $0.0002 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
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…