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 latestaiagents/agent-skills --skill product-demo-videogit clone --depth 1 https://github.com/latestaiagents/agent-skillsWrote 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/latestaiagents/agent-skills/product-demo-video)<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/product-demo-video"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/product-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/latestaiagents/agent-skills/product-demo-video"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/product-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 | $0.00129 | $0.01646 |
| Opus 5.5 | $0.00052 | $0.00658 |
| Sonnet 5.5 | $0.00026 | $0.00329 |
| Haiku 4.5 | $0.00013 | $0.00165 |
Grade A, and why
product-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 9d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Demo Video
A demo video shows one user achieving one outcome, in a clean environment, at a pace a newcomer can follow.
When to Use
- Announcing a feature or release
- Onboarding or help-centre walkthroughs
- Landing-page hero loops and social clips of the product
- Turning a manual QA flow into a repeatable, re-recordable demo
When NOT to Use
- Pure motion-graphics explainers with no product UI: use
video-production-pipeline - Bug reproduction videos for engineers: record raw, no editing needed
Workflow
Step 1: Define the Story
Write the outcome as one sentence: "A new user connects Slack and gets their first alert." Then list the minimum clicks to get there. Cut every step that is not on that path (settings tours, alternative routes, edge cases).
Plan the length from the shot list, and split long flows into a series rather than one long video.
Step 2: Prepare a Clean, Safe Demo Environment
- Use seeded demo data. Never record production customer data, real emails, API keys, or internal URLs.
- Use a dedicated demo account with a neutral name and avatar.
- Hide notifications and personal bookmarks; close unrelated tabs and apps.
- Fix the window size to the target resolution (for example 1920×1080) and set browser zoom so text is legible when scaled down.
- Set the UI to a known state (light or dark theme, language, feature flags) and document it, so the demo can be re-recorded after the next UI change.
- Disable animations or loaders that make timing unpredictable, if the app has a setting for it.
Step 3: Record
Pick the recording method by how often the demo will be re-shot.
| Method | Use when | Notes |
|---|---|---|
| macOS Screenshot toolbar (Shift-Command-5) | One-off, quick recordings on a Mac | Record the entire screen or a selected portion; saves a .mov |
| OBS Studio | Cross-platform, multiple sources, webcam overlay | Free and open source; configure output resolution and frame rate to match the edit |
Playwright recordVideo |
The demo should be reproducible and re-recorded after UI changes | Scripted, deterministic clicks; no cursor jitter |
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.
- 9d ago First seen · 136 lines · 129 tokens per session scan A 9f32407b3363
product-demo-video is a skill published in the GitHub repository latestaiagents/agent-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 129 tokens to every session and 1,646 once invoked, about $0.0005 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 2026-11-04.
product-demo-video compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-demo-videolatestaiagents/agent-skills | Skill | 6 | 9d ago | MIT | A | 129 | Claude Code |
| ai-browser-useskillsaiagent/aiskills | Skill | 5 | 5mo ago | none | A | 71 | Codex |
| nexent-daily-testModelEngine-Group/nexent | Skill | 6.2k | today | MIT | A | 78 | Claude Code, Codex |
| site-auditbrennhill/Kaboom-Browser-AI-Devtools-MCP | Skill | 67 | 25d ago | AGPL-3.0 | A | 34 | Claude Code, Codex |
| automatebrennhill/Kaboom-Browser-AI-Devtools-MCP | Skill | 67 | 25d ago | AGPL-3.0 | A | 35 | Claude Code, Codex |
| pr-dashboardMarieLynneBlock/arcanum-artifex | Skill | 4 | 1mo ago | none | A | 61 | Claude Code, Codex |
| ai-humanizer-zhskillsaiagent/aiskills | Skill | 5 | 5mo ago | none | A | 81 | Codex |