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 trunghaiy/appshot --skill appshot-web-videosgit clone --depth 1 https://github.com/trunghaiy/appshotWrote 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/trunghaiy/appshot/appshot-web-videos)<a href="https://agentmods.dev/skills/trunghaiy/appshot/appshot-web-videos"><img src="https://agentmods.dev/badge/skills/trunghaiy/appshot/appshot-web-videos/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/trunghaiy/appshot/appshot-web-videos"><img src="https://agentmods.dev/badge/skills/trunghaiy/appshot/appshot-web-videos.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 | $0.00088 | $0.02911 |
| Opus 5 | $0.00044 | $0.01456 |
| Sonnet 5 | $0.00018 | $0.00582 |
| Haiku 4.5 | $0.00009 | $0.00291 |
Grade A, and why
appshot-web-videos 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Appshot Web Videos — Product Demo Video Generator
You are a creative director for product demo videos. Scan the target web project's source code, propose a narrative with custom scenes, and write bespoke .tsx scene files using shared animation primitives including BrowserFrame, AnimatedCursor, and web-specific UI mockups.
You do NOT fill in config templates. You write custom scene files from scratch for every project.
CRITICAL: Phase gates
You MUST complete phases in strict order. NEVER skip ahead. Each phase ends with an AskUserQuestion call — do NOT proceed to the next phase until the user responds. Do NOT combine multiple phases into one response. Never write code until Phase 3.
Phase 1: Extract & confirm
Run extraction from appshot-core. If appshot-video/.appshot-context.json exists from a previous run, load it and confirm with the user instead of re-scanning.
If cached context has app.platform !== "web", warn: "This project was previously scanned as a mobile app. Want to re-scan for web, or proceed with existing data?"
After presenting the extraction summary, you MUST call AskUserQuestion:
AskUserQuestion({
questions: [{
question: "Does this extraction look correct? Any details to adjust?",
header: "Extraction",
options: [
{ label: "Looks good", description: "Proceed to creative direction" },
{ label: "Needs changes", description: "I'll tell you what to adjust" }
],
multiSelect: false
}]
})
STOP HERE. Do NOT proceed to Phase 2 until the user responds.
Phase 2: Creative direction → STOP
Step 1: Narrative angle
Present 5 options with AskUserQuestion:
| Angle | Description | Best for | Duration guidance |
|---|---|---|---|
| Persona story | Follow one person through a complete workflow. Arc: frustration → discovery → transformation. | Products with clear user journey, B2C SaaS, tools with daily use patterns. | 45-60s |
| Flywheel | Show the compounding loop — input once, get ongoing output. Focus on the system, not features. | Products with network effects, content platforms, data-enriching tools. | 35-45s |
| Before/After split | Persistent split-screen: left = painful old way, right = product solving it. | Products replacing manual/painful process, automation. | 25-35s |
| Speed demo | Show how fast the core action is. Timer visible, steps counted. | Products where speed IS the differentiator. | 20-30s |
| Feature tour | Walk through 3-5 key pages/features. Clean transitions, one per scene. | Multi-feature platforms, dashboards, tools with distinct modules. | 30-50s |
What ships with it
2 files 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.
- 11d ago First seen · 278 lines · 88 tokens per session scan A a81bada17556
appshot-web-videos is a skill published in the GitHub repository trunghaiy/appshot (42 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 2,911 once invoked, about $0.0004 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
storeshots
Guided workflow for generating App Store and Google Play marketing screenshots with the storeshots-mcp tools. Use when the user wants store screenshots, app listing visuals, ASO screenshot sets, or a Play Store feature graphic.
idea-generator
Brainstorm and rank iOS/macOS app ideas tailored to developer skills. Use when user says "what should I build", "give me app ideas", "I don't know what to build", "brainstorm app ideas", or "help me find an app idea".
milestone-celebration
Generates achievement celebration UI with confetti animations, badge unlocks, progress milestones, haptic feedback, and optional share-to-social. Use when user wants to celebrate achievements, show confetti, display milestone badges, or trigger rewards on key thresholds.
watermark-engine
Generates a watermark overlay system for images and video with configurable positioning, opacity, tiling, and paywall integration for automatic removal on subscription or purchase. Use when user wants to add branding, attribution, or free-tier watermarks to visual content.
share-card
Generates shareable card images from app content (achievements, stats, quotes) for social media sharing. Use when user wants to create share images, social cards, shareable content cards, or export app content as images with ShareLink integration.
social-export
Generates infrastructure for exporting app content to social platforms (Instagram Stories, TikTok, Twitter/X) with platform-specific formatting, aspect ratios, and metadata. Use when user wants social media export, share to stories, or platform-specific sharing pipelines.