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.
git clone --depth 1 https://github.com/Kminer2053/demo-video-skillWrote 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/rules/kminer2053/demo-video-skill/demo-video)<a href="https://agentmods.dev/rules/kminer2053/demo-video-skill/demo-video"><img src="https://agentmods.dev/badge/rules/kminer2053/demo-video-skill/demo-video/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/rules/kminer2053/demo-video-skill/demo-video"><img src="https://agentmods.dev/badge/rules/kminer2053/demo-video-skill/demo-video.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 | $0.00054 | $0.00411 |
| Opus 5.5 | $0.00022 | $0.00164 |
| Sonnet 5.5 | $0.00011 | $0.00082 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
demo-video 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.
What it actually says
Demo Video (Playwright + ffmpeg)
When the user wants a demo video / feature walkthrough / product demo / screen recording of a localhost app — even phrased as "make something that shows this feature running" — drive and record the real running app headlessly with Playwright and bake in overlays in code. This is for real screen-operation demos, NOT motion-graphic teasers.
Core ideas:
- Inject the overlay (subtitle bar, feature label, fake cursor) on
document.documentElement(html), NOTbody— zoom transformsbody, so an html-level overlay is immune to zoom. - A fake cursor (SVG + CSS transition) stages the mouse; the real one is invisible headless.
- LLM/loading waits use
waitForFunction(never a fixed sleep); recordwaitMsand speed up only that window 6–9x with ffmpeg.
Workflow (fixed order): script the scene table & get approval → environment check (never kill the
user's server) → build ONE PoC scene & get tone approved → capture scenes with
scripts/cap_scene.template.js (replace only the SEQUENCE block) → post-process & montage-QA per
scene with scripts/postprocess.sh → concat into the montage → confirm with user real playback.
Non-negotiables: ctx.close() before browser.close() (flushes the webm); goto with
waitUntil:'networkidle'; speed-up on wait windows is mandatory.
Full detail: read references/playbook.md. Full skill: SKILL.md / AGENTS.md.
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 · 30 lines · 54 tokens per session scan A 3319ce1afb17
demo-video is a cursor rule published in the GitHub repository Kminer2053/demo-video-skill (27 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 411 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 2026-08-30.
Other cursor rules, from other repositories
chrome-extension-dev-js-typescript-cursorrules-pro
Cursor rules for VSCode extension development with Electron and TypeScript integration.
javascript-chrome-apis-cursorrules-prompt-file
Cursor rules for JavaScript development with Chrome APIs integration.
chrome-extension-general-rules
General Chrome extension rules guide architecture, security, performance, and integration with an existing project. They cover JavaScript, TypeScript, HTML, CSS, browser APIs, and several interface libraries.
browser-api-usage-rules
Chrome browser API rules cover browser extension interfaces such as tabs, storage, and runtime. They require error handling and recommend Chrome alarms for scheduled work instead of setInterval.
extension-architecture-rules
Architecture guidelines for Chrome extensions that separate each part of the extension and let those parts communicate through messages and shared storage.
real-browser-mcp
Instructions for using Real Browser MCP to control the user's actual browser.