cloud-screencast

A tool for recording repeatable product-demo videos of a web app on a temporary Google Cloud computer. It opens the app in Chrome, follows scripted interactions, records the screen, and cuts the result into a shareable clip.

In plain words
What is it for?
Use it to deploy a web app on a temporary cloud machine, drive its interface with Playwright, record the browser, and produce a social-ready demo video. Delete the cloud machine after downloading the recording to stop further charges.
Why use it?
It avoids personal data, inconsistent screen sizes, and accidental actions that can appear in recordings made on a developer’s computer. The scripted recording can be repeated until the take is right.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/oratis/lisa/cloud-screencast
Any agent
npx skills add oratis/LISA --skill cloud-screencast
Clone the repo
git clone --depth 1 https://github.com/oratis/LISA

Made for: Claude Code, Codex.

Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,346 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00154 $0.03346
Opus 5 $0.00077 $0.01673
Sonnet 5 $0.00031 $0.00669
Haiku 4.5 $0.00015 $0.00335

Measured 3d ago against content hash 4b0c44d77a6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

cloud-screencast scanned grade D with 2 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 3d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (reference/edit.sh, reference/music.sh, reference/setup.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

ssh ... "mkdir -p ~/.app && cat > ~/.app/config.env && chmod 600 ~/.app/config.env"

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

# each retake starts with: rm -rf ~/.app && cp -r ~/.app-pristine ~/.app
.claude/skills/cloud-screencast/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cloud-screencast — reproducible UI demo videos on a throwaway VM

Records a web UI on a headless cloud box instead of the user's desktop. You get a pristine app state, a chosen viewport, no personal data in frame, and a scripted take you can re-run until it's right — none of which is true of a hand-recorded local screen capture.

Cost + lifecycle: this creates a billable VM. Always tell the user it exists, and delete it when the recording is downloaded (§8). An e2-standard-4 left running is roughly $95/month.


Config

Fill once per project, then run.

PROJECT   = <gcp-project-id>
ZONE      = <zone, e.g. us-central1-a>
VM        = <instance-name, e.g. app-record>
APP_REPO  = <git url of the app, or an npm package name>
APP_START = <command that serves the UI, e.g. node dist/cli.js serve --web --port 5757>
APP_URL   = <local url the browser opens, e.g. http://127.0.0.1:5757/>
SECRETS   = <local env file the app needs, e.g. ~/.app/config.env>

1. Pick the geometry first

Everything downstream depends on this, and getting it wrong means re-recording.

Chrome's --force-device-scale-factor=N divides the X display into CSS pixels:

CSS viewport = Xvfb resolution / DSF

Record at 2× the delivery resolution and downscale in post — supersampling is what makes small UI text look sharp in an H.264 clip.

Delivery Xvfb DSF CSS viewport Notes
1920×1080 2880×1620 2 1440×810 good default, 16:9
1920×1080 2560×1440 2 1280×720 tighter; short UIs get clipped
1080×1080 2160×2160 2 1080×1080 square, better mobile in-feed

Do not just use 1280×720. A real user's browser window is far taller than 720 CSS px, so a 720-tall viewport clips panels that never clip in real life — and the clipped part is usually the payoff (the final state, the confirm button). Probe the actual content height before committing (§4) and go taller if it overflows.

Keep integer DSF values. Fractional scale factors make Chrome's text rendering noticeably softer.

Read the full file on GitHub · 300 lines

Files

What ships with it

5 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.

Changes

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.

  1. 3d ago First seen · 300 lines · 154 tokens per session scan D 4b0c44d77a6c

Subscribe to this mod's changes

cloud-screencast is a skill published in the GitHub repository oratis/LISA (173 stars, last pushed 6d ago), licensed MIT. It adds 154 tokens to every session and 3,346 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

eliza-cloud

Use when the task involves Eliza Cloud or elizaOS Cloud as a managed backend, app platform, deployment target, billing layer, or monetization surface. The catch-all skill for any user request about THEIR existing apps / containers / earnings / credits / api-keys / analytics / billing / payment requests / payouts …

elizaOS/eliza · 191 tokens

eliza-cloud-manage-domain

Use after a domain has been purchased through Eliza Cloud (via the eliza-cloud-buy-domain skill) when the user wants to look at, edit, or remove a domain or its DNS records. Covers org-wide domain listing, per-app DNS record CRUD on cloudflare-managed zones, status re-sync, external-attachment verification, and…

elizaOS/eliza · 125 tokens

local-tools

Access local system resources including Calendar on macOS and Windows. Use this skill when you need to manage user's schedule directly on their device.

netease-youdao/LobsterAI · 30 tokens

seedance

Generate AI videos using Volcengine Seedance model. Supports text-to-video (T2V), image-to-video (I2V), and audio-synced video generation. Use this skill when the user wants to create or generate videos.

netease-youdao/LobsterAI · 52 tokens

seedream

Generate AI images using Volcengine Seedream model. Supports text-to-image (T2I), image editing (I2I), multi-image fusion, and web-search-based generation. Use this skill when the user wants to create, generate, or edit images.

netease-youdao/LobsterAI · 56 tokens

technology-search

Search tech blogs, developer forums, and IT media (TechCrunch, Hacker News, 36氪, etc.) for software and hardware industry updates with heat ranking and EN↔CN translation. Use this skill only when the topic is clearly about programming, software, hardware, AI, or IT infrastructure.

netease-youdao/LobsterAI · 65 tokens