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 oneworks-ai/app --skill oneworks-plugin-uigit clone --depth 1 https://github.com/oneworks-ai/appWrote 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/oneworks-ai/app/oneworks-plugin-ui)<a href="https://agentmods.dev/skills/oneworks-ai/app/oneworks-plugin-ui"><img src="https://agentmods.dev/badge/skills/oneworks-ai/app/oneworks-plugin-ui/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/oneworks-ai/app/oneworks-plugin-ui"><img src="https://agentmods.dev/badge/skills/oneworks-ai/app/oneworks-plugin-ui.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 | $0.00070 | $0.00483 |
| Opus 5.5 | $0.00028 | $0.00193 |
| Sonnet 5.5 | $0.00014 | $0.00097 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade A, and why
oneworks-plugin-ui 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 2mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OneWorks Plugin UI
Read apps/client/src/plugins/AGENTS.md, the target plugin's nearest AGENTS.md, and .oo/skills/ui-design-memory/SKILL.md before editing.
Map the host before markup
Write down which layer owns each visible responsibility:
- route identity and selected resource name:
view.route.setTitle(...); - hierarchy and back navigation:
view.route.setBreadcrumb(...); - collection resources and search:
view.route.setSidebar(...); - stable collection shortcuts beside the owning sidebar entry:
nav.items[].actions; - commands on the object currently named by the header:
view.route.setActions(...); - focus/reconnect cache revalidation:
view.data.useQuery(...); - embedded shared UI:
view.ui.*, using flush/inset options when the route owns outer spacing.
The plugin body starts with actual content. Do not repeat a title already visible in the route header or breadcrumb. Do not place collection navigation in object actions. Do not add a refresh action when query revalidation is sufficient. Do not make both host and embedded content own the same padding.
Extend the host conservatively
If a needed placement or behavior is missing, add a structured, plugin-agnostic host contract and consume it from the plugin. Do not imitate host chrome with plugin-local DOM/CSS and do not add package-name branches to the host.
Verify the whole route
Check the root resource view and every secondary state at desktop and narrow widths. Assert:
- one visible owner for page identity;
- selected resource title updates in the shared header;
- sidebar actions stay beside their owning entry and navigate without reload;
- breadcrumbs are the only duplicate-free return path;
- header actions operate on the current object only;
- no redundant refresh or open-current-view action;
- no duplicated outer padding;
- focus/reconnect revalidation and post-mutation
mutate()work.
Complete the independent revision-bound visual review required by $ui-design-memory before delivery.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 42 lines · 70 tokens per session scan A 41bf211bb23d
oneworks-plugin-ui is a skill published in the GitHub repository oneworks-ai/app (20 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 483 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 2026-08-30.
Other skills, from other repositories
openai-frontend-design
Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the user explicitly asks for a redesign/restyle/modernization. Builds from clean, airy, high-taste, readable image-generated concept design with section-specific references, faithful…
ultralytics-branding
This skill should be used when creating Ultralytics-branded content of any kind, including PDF, PPTX, Canva, or Google Slides presentations, DOCX documents, marketing or newsletter HTML emails, social media post copy or visuals, website or landing page designs, and dataset or model result visuals. Provides official…
email-design
This skill should be used when user asks to "design app emails", "theme transactional emails", "fix verification emails", "build email templates", or "review password reset emails". Match an app’s brand and reuse its delivery pipeline across account, billing and notification emails.
a11y-audit
Run a Maestro-style accessibility audit for WCAG compliance, ARIA usage, keyboard navigation, and screen reader compatibility.
lov-mobile-infographic
A mobile infographic maker that turns existing conclusions, research, or conversation content into a tall, phone-readable card. It delivers editable HTML and a PNG image.
lov-maintain-partners
Maintain the Skill Publisher website's partners section AND align partner logo rows on event posters / hero strips: reuse lov-find-logo for brand logo discovery, normalize collected logos to a 240px-tall content canvas (retina-ready), rasterize SVGs via rsvg-convert before normalizing (so SVG viewBox padding gets…