Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.
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 Orkas-AI/Orkas --skill ui-controls-accessibilitygit clone --depth 1 https://github.com/Orkas-AI/OrkasWrote 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/orkas-ai/orkas/ui-controls-accessibility)<a href="https://agentmods.dev/skills/orkas-ai/orkas/ui-controls-accessibility"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/ui-controls-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/orkas-ai/orkas/ui-controls-accessibility"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/ui-controls-accessibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00004 | $0.01426 |
| Opus 5 | $0.00002 | $0.00713 |
| Sonnet 5 | $0.00001 | $0.00285 |
| Haiku 4.5 | $0.00000 | $0.00143 |
Grade A, and why
ui-controls-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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ui-controls-accessibility
Requested Outcome Gate
Before rendering, turn every explicitly requested workflow outcome into a compact ledger: user outcome -> triggering control/event -> rendered state branch -> recovery/next action. Success and failure are separate outcomes. When a backend is unavailable but the outcome can be modeled locally, make both outcomes reachable through the primary control flow with documented sample inputs or a deterministic local mock resolver. Preview controls may supplement this proof, but they must not be the only route to an ordinary product failure state. Use distinct preview controls only when no credible primary-flow trigger exists. Do not deliver while any requested outcome exists only in prose, an unreachable conditional, an ambiguous shared trigger, or a generic error state from a different step.
Use this specialist for complex forms, non-trivial composite widgets, accessibility audits, or control/state failures that need deeper guidance. Ordinary controls, focus, labels, and responsive behavior are covered by ui-design-executor and do not require loading this skill.
Control Taxonomy
Use familiar controls for the job:
- Button: clear command.
- Icon button: familiar compact command, with tooltip or accessible label.
- Toggle or checkbox: binary setting.
- Radio group: mutually exclusive choice where every option should be visible.
- Segmented control: small mode set that changes a view or filter.
- Select or combobox: larger option set.
- Menu: secondary commands.
- Tabs: peer views with persistent context.
- Slider: continuous numeric adjustment.
- Stepper or numeric input: precise numeric adjustment.
- Table or grid: comparison and repeated scanning.
- Drawer: secondary workflow while preserving main context.
- Modal: blocking decision or short focused task.
- Tooltip: explain an icon or concise unfamiliar label, not required content.
Do not style decorative pills as controls unless they have standard keyboard and state behavior.
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.
- 9d ago First seen · 112 lines · 4 tokens per session scan A 9c661c638a7d
ui-controls-accessibility is a skill published in the GitHub repository Orkas-AI/Orkas (1,808 stars, last pushed yesterday), licensed MIT. It adds 4 tokens to every session and 1,426 once invoked, about $0.0000 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
tutti-ui-system
Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.
cross-border-listing-image-layout-audit
Audit listing image and layout notes — first-impression hero, info hierarchy, lifestyle vs studio, copy density, trust signals, compliance — into a follow-up checklist.
design-plan-review
Reviews a UI or UX plan before implementation.
excalidraw-diagram-generator
Converts textual concepts or workflows into clear diagram instructions suitable for Excalidraw or other visual tools.
infographic-builder
Turns textual content into structured infographic formats suitable for reports, presentations, and educational materials.
ui-ux-layout-advisor
Advises on interface layouts to optimize clarity, spacing, hierarchy, and usability.