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 glifxyz/glif-mcp-server --skill app-demo-videosgit clone --depth 1 https://github.com/glifxyz/glif-mcp-serverWrote 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/glifxyz/glif-mcp-server/app-demo-videos)<a href="https://agentmods.dev/skills/glifxyz/glif-mcp-server/app-demo-videos"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/app-demo-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/glifxyz/glif-mcp-server/app-demo-videos"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/app-demo-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 | $0.00192 | $0.01451 |
| Opus 5.5 | $0.00077 | $0.00580 |
| Sonnet 5.5 | $0.00038 | $0.00290 |
| Haiku 4.5 | $0.00019 | $0.00145 |
Grade A, and why
app-demo-videos scanned grade A with 1 finding 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 17d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Download with `curl -fsSL "<media url>" -o <path>` into `marketing/video/`, or `public/videos/` if the site embeds it. Check: How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record the real app, then let Glif frame it in a video template. The user's explicit instructions come first, within host safety rules.
1. Plan the video
Agree on a short plan before recording:
- Story: 3 to 6 beats, one feature or action each. Open with the most useful moment; social cuts need a hook in the first 3 seconds.
- Length: 15 to 30 seconds for social and teasers, 30 to 90 for walkthroughs and explainers.
- Template: pick one, or describe your own.
- Browser tour: the app in a clean browser window on a soft background, zooms on clicks, a caption per beat.
- Device composite: the real recording placed on a laptop or phone screen in a generated lifestyle scene. Glif tracks the screen if the camera moves.
- Social ad demo: vertical, 15 seconds, hook first, big captions, music.
- Narrated walkthrough: voiceover and captions over the browser tour.
- Explainer: animated slides in a chosen style, narrated, with short clips of the real app. Good for "how it works".
- Changelog video: release notes or a changelog URL turned into a short narrated update.
- App Store preview: real app footage only, 15 to 30 seconds, vertical. Check App Store Connect for current specs.
- Outputs: 16:9 master at 1920×1080, plus a 9:16 1080×1920 cut if wanted, a poster image, a 1280×720 YouTube thumbnail or a README GIF.
- Sound: voiceover script, voice (Glif can play samples to choose from, or clone a voice from a sample with the owner's consent), music mood (ducked under the voice), and optional click sounds synced to the cursor.
- Captions: word-by-word highlight, simple lower thirds, or motion-graphic overlays with numbers and charts. Ask Glif for a still frame with a few font options first if the look matters.
Show the plan and wait for a yes. Video uses more credits than images.
2. Record the app
Use the user's own recording or Loom export if they have one. Otherwise:
- Start the app locally and seed it with demo data. Never record real customer data, emails, tokens or keys.
- Copy
scripts/record-demo.mjsinto the project's scratch space. Install Playwright if the project lacks it (npm i -D playwrightandnpx playwright install chromium), after checking with the user. - Replace the example beats with the planned steps.
glideClickmoves a visible cursor before clicking.smoothScrollscrolls gently. Leave about a second of stillness after each beat. - Run it with
DEMO_URL=<local url> node record-demo.mjs. AddDEMO_MOBILE=1for a phone layout. It prints each beat's time; keep those for captions. - Check the result, or pull frames with
ffmpeg -ss <seconds> -i <file> -frames:v 1 frame.png. Re-record if something glitched. - If
ffmpegis installed, convert to MP4:ffmpeg -i in.webm -c:v libx264 -pix_fmt yuv420p -crf 18 demo-raw.mp4.
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.
- 17d ago Changed · -1 tokens per session ddf9dc97b870
- 18d ago First seen · 76 lines · 193 tokens per session scan A 8bda2b6cb5a7
app-demo-videos is a skill published in the GitHub repository glifxyz/glif-mcp-server (216 stars, last pushed 17d ago), licensed MIT. It adds 192 tokens to every session and 1,451 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-binary-and-data
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…
n8n-code-tool
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the query input, returning a string result, defining an input schema…
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
n8n-expression-syntax
Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, mapping data between nodes, or referencing webhook data in workflows. Use this skill whenever configuring node fields that reference data from…