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 ABO3SKRALMASAOODI/valmera-mcp --skill website-demo-videogit clone --depth 1 https://github.com/ABO3SKRALMASAOODI/valmera-mcpWrote 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/abo3skralmasaoodi/valmera-mcp/website-demo-video)<a href="https://agentmods.dev/skills/abo3skralmasaoodi/valmera-mcp/website-demo-video"><img src="https://agentmods.dev/badge/skills/abo3skralmasaoodi/valmera-mcp/website-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/skills/abo3skralmasaoodi/valmera-mcp/website-demo-video"><img src="https://agentmods.dev/badge/skills/abo3skralmasaoodi/valmera-mcp/website-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 | $0.00062 | $0.00576 |
| Opus 5.5 | $0.00025 | $0.00230 |
| Sonnet 5.5 | $0.00012 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
website-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 14d 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make a website or product demo video with Valmera
Valmera can drive a real browser through a public website, recording a visible cursor that clicks, scrolls and types. It can then cut the recording like a product video, with zooms that follow each click.
Workflow
- Create a project with
create_project, or open the user's project. - Plan a short story. Write 4–10 steps that show one clear flow, such as the landing page, then the key feature, then the call to action. A demo that clicks everything shows nothing. Ask the user for the URL and the one thing viewers must understand.
- Record. Call
record_website_demowith the URL, an orientation (landscapefor websites,portraitfor social) and the steps. Steps look like{do:'click', text:'Get started'},{do:'scroll', to:'Pricing'},{do:'hover', text:'Plans'},{do:'type', selector:'input[type=email]', text:'[email protected]'}and{do:'wait', seconds:1.5}. It records the public site as a visitor sees it, and never types into password or payment fields. For a simple scrolling capture, userecord_website. - Cut it like a product video. Call
showcase_demowith the recorded clip. It places the clip and adds zooms that travel between the clicks. For a recording the user uploaded, passclick_times, and useenhance_cursorandadd_zoom_pathwhen the pointer is hard to follow. - Add the story layer. Add a title card (
add_title_card), short on-screen text for each step (add_text), music (add_music), and a closing call to action. - Render and check. Call
render_preview, thenwait_for_job, thenlook_atwithrendered=trueat each click, so you can confirm the zooms land on the right element. - Export when asked. Call
export_final, thenwait_for_job, thendownload_urlwithkind="final".
Limits
- Only public pages can be recorded. Desktop apps and logged-in areas can't, so ask the user to upload their own screen recording for those.
- Editing requires a Valmera subscription (https://valmera.io/subscribe).
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.
- 14d ago First seen · 24 lines · 62 tokens per session scan A 6b2f884e4fa4
website-demo-video is a skill published in the GitHub repository ABO3SKRALMASAOODI/valmera-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 62 tokens to every session and 576 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 2026-10-06.
Other skills, from other repositories
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
qa-testing-playwright
Builds and debugs Playwright E2E suites. Use when authoring browser tests, fixing flakes, or hardening Playwright CI and locator strategy.
qa-persona-testing
Tests apps as an ICP persona through browser automation and reports friction, fixes, and risks. Use when running persona-based, ICP, or synthetic-user testing.
proof-e2e
Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to "write E2E tests", "end-to-end testing", "browser tests", "UI tests", or "Playwright tests".
browser
Interactive browser automation via playwright-cli. Use when you need to navigate a site, click elements, fill forms, take snapshots, or triage a live app.
watch
Open the Roundtable office in the browser — a live, read-only view of this machine's Claude Code sessions, with every subagent as a person at a desk and a timeline you can rewind.