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 XyrusCode/ai-sync --skill widgetgit clone --depth 1 https://github.com/XyrusCode/ai-syncWrote 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/xyruscode/ai-sync/widget)<a href="https://agentmods.dev/skills/xyruscode/ai-sync/widget"><img src="https://agentmods.dev/badge/skills/xyruscode/ai-sync/widget/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/xyruscode/ai-sync/widget"><img src="https://agentmods.dev/badge/skills/xyruscode/ai-sync/widget.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 | $0.00055 | $0.02212 |
| Opus 5.5 | $0.00022 | $0.00885 |
| Sonnet 5.5 | $0.00011 | $0.00442 |
| Haiku 4.5 | $0.00006 | $0.00221 |
Grade A, and why
widget 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Widget
Widget owns one responsive index.html, display data, input state, events, files, and workspace resources. Every surface renders data.metadata.roots.workspaceRoot/index.html.
Create And Show
Create the Widget definition first:
{
"action": "create",
"title": "Status card",
"description": "Shows the latest pipeline status.",
"type": "html",
"creationHints": ["Checking live status", "Preparing the status card"]
}
Then:
- Write a complete HTML document to
data.metadata.roots.workspaceRoot/index.html. - Call
Widget.validate. - For conversation or dock display, call
Widget.show. - For Canvas display, call
Canvas.placeWidgetwith the returnedwidgetId.
creationHints accepts 1-6 short progress lines. The host displays them while the page is being authored. Static Widgets need no slots, events, Binding, or Automation.
For appearance and responsive layout, load widgetdesign/SKILL.md before writing HTML/CSS. It is
the self-contained Widget design authority; do not load another Widget Design Skill for the same
work.
Inspect And Modify An Existing Widget
- Resolve the Widget with
Widget.listor a knownwidgetId; followdata.page.nextOffset. - Call
Widget.readand inspect its slots, events, active Binding, status, input state, latest data, anddata.metadata.roots.workspaceRoot. - Read the existing
index.htmlbefore editing it. Preserve working behavior unless the user requested a replacement. - If metadata, slots, or events change, call
Widget.updateand inspectrevalidatedBindings. Do not call update merely to activateindex.html. - Write the updated complete document, then call
Widget.validateand repair any invalid owning contract before running again. - If the Widget has an active Binding, call
Binding.validateafter page or resource changes and inspect its current status before running the Automation. - Confirm an existing mounted view refreshed, or call
Widget.showwhen conversation/dock display is requested.
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.
- 1mo ago First seen · 221 lines · 55 tokens per session scan A 4820b9903f87
widget is a skill published in the GitHub repository XyrusCode/ai-sync (2 stars, last pushed 18d ago), licensed MIT. It adds 55 tokens to every session and 2,212 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.