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 Kevin-Liu-01/Sigil-UI --skill sigil-scenegit clone --depth 1 https://github.com/Kevin-Liu-01/Sigil-UIWrote 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/kevin-liu-01/sigil-ui/sigil-scene)<a href="https://agentmods.dev/skills/kevin-liu-01/sigil-ui/sigil-scene"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/sigil-ui/sigil-scene/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/kevin-liu-01/sigil-ui/sigil-scene"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/sigil-ui/sigil-scene.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 | $0.00125 | $0.01528 |
| Opus 5 | $0.00063 | $0.00764 |
| Sonnet 5 | $0.00025 | $0.00306 |
| Haiku 4.5 | $0.00013 | $0.00153 |
Grade A, and why
sigil-scene 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 11d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — sigil-scene
One scene per file. The page composes scenes. Animation lives next to its rendering. Tokens drive timing.
What is a "scene"?
A scene is a self-contained named visual or animated block that the page
composes — for example HeroDiagram, PresetMorphScene, CliVoronoi,
LayerStackDemo. Scenes are NOT generic components: they're page-specific,
they may own state and keyframes, and they exist primarily to extract long
inline JSX out of app/page.tsx-style files.
The convention solves the "1,300-line page.tsx" problem: each named visual
becomes its own file, the page becomes a thin composition file, and an agent
asked to "tweak the hero diagram animation" can grep HeroDiagram.scene.tsx
or HeroDiagram.tsx and find everything in one place.
Where scenes live
apps/web/components/landing/scenes/
PresetMorphScene.tsx ← extracted from app/page.tsx
CliDiagram.tsx ← skeleton diagrams + voronoi math
HeroDiagram.tsx ← (when extracted)
...
The naming convention is PascalCase + descriptive (PresetMorphScene,
not MorphScene). The Scene suffix is optional for unambiguous names like
CliDiagram or HeroLogoField.
When to extract a scene
Extract into a scene file when ANY of the following are true:
- Inline JSX block exceeds ~80 lines
- The block owns its own
useState/useEffect - The block injects its own
<style>or@keyframesblock - The block defines its own data const (e.g.
MINI_PRESETS,CLI_VORONOI_TILES) - The block needs to be reused on more than one page
Do NOT extract when:
- The block is < 30 lines and has no state
- The block is tightly coupled to the page's
LandingSection/ shared helpers - Extraction would require re-importing the same
useOptional*hooks
Scene file structure
// apps/web/components/landing/scenes/HeroDiagram.tsx
"use client";
import { useState } from "react";
import { /* @sigil-ui/components imports */ } from "@sigil-ui/components";
/* Scene-local data constants live at the top of the file. Export them
if the page composes the scene across multiple instances, otherwise
keep them private. */
export const HERO_PRESETS = [/* ... */];
/* Local types for the scene's public shape. */
export type HeroDiagramProps = {
index: number;
setIndex: (i: number) => void;
};
/* The scene itself. Owns its render, state where applicable,
keyframes (inline `<style>` block at the bottom), and any
pure helpers that aren't worth a separate file. */
export function HeroDiagram({ index, setIndex }: HeroDiagramProps) {
return (
<div /* ... */>
{/* render */}
</div>
);
}
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.
- 11d ago First seen · 169 lines · 125 tokens per session scan A 406c0f347fc0
sigil-scene is a skill published in the GitHub repository Kevin-Liu-01/Sigil-UI (9 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 1,528 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…
port-sacred-terminal-ui-to-hostile-react-codebase
Take a sacred React component (or a sacred screen that mirrors a Simulacrum CLI surface) and graft it into a foreign React codebase that already ships its own design system, build pipeline, and CSS toolchain — without breaking the host or polluting it with sacred-specific globals.
port-sacred-terminal-ui-to-react-using-same-conventions
Take a CLI screen written for Simulacrum — the sacred CLI framework (scripts/cli/templates/.ts or scripts/python/templates/.py) — and produce a React component that lives inside components/examples/ (or components/) using only sacred's existing primitives — Window, Card, SimpleTable, ActionButton, RowSpaceBetween…
ss-motion
Apply a named StyleSeed motion to a component — either one of the 5 personality seeds (Spring/Silk/Snap/Float/Pulse × entrance/exit/hover/press/layout) or a distinctive keyword move from the motion library (toggle-flip, toggle-curtain, reveal-blur, pop-in, shimmer, …). Translates vibe words into framer-motion code…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
ss-verify
The VISUAL gate — render a UI or visual artifact through its surface adapter, inspect the actual pixels, then fix and re-render until it passes the composed StyleSeed rule set.