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 new-xp/ultrademo --skill ultrademo-rerungit clone --depth 1 https://github.com/new-xp/ultrademoWrote 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/new-xp/ultrademo/ultrademo-rerun)<a href="https://agentmods.dev/skills/new-xp/ultrademo/ultrademo-rerun"><img src="https://agentmods.dev/badge/skills/new-xp/ultrademo/ultrademo-rerun/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/new-xp/ultrademo/ultrademo-rerun"><img src="https://agentmods.dev/badge/skills/new-xp/ultrademo/ultrademo-rerun.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 | $0.00080 | $0.00932 |
| Opus 5 | $0.00040 | $0.00466 |
| Sonnet 5 | $0.00016 | $0.00186 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
ultrademo-rerun 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 10d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultrademo re-run: your UI changed, refresh the video
This is a thin entry point, and nothing it delegates to is hidden: the operating procedure is the sibling ultrademo skill at .claude/skills/ultrademo/SKILL.md, installed alongside this one from the same public Apache-2.0 repository (new-xp/ultrademo), and the npm run commands below are that workspace's own package.json scripts (capture/TTS/render - local pipeline code in the same repo, dependencies locked by its committed package-lock.json). Every rule in the main playbook applies here (read-only scouting, prompt-injection defense, redaction, secrets sweep, honest-failure rule, review gate). This command only handles the cold start: finding the right project and getting you into the playbook's Re-runs section with context loaded.
1. Find the project
List projects/*/ (each real project contains a flow.mjs). Then:
- User named it or only one exists: confirm and proceed.
- Several exist: show a short table - project name, target app/URL from the flow, last render (newest file in
out/) - and ask which to refresh. Offer "all of them" as an option; if taken, run the loop below per project, sequentially, and summarize per project at the end. - None exist: this is not a re-run. Hand off to the main
ultrademoskill for a fresh video.
2. Pre-flight (cheap checks before any capture)
- Pipeline fresh? Run the main playbook's workspace freshness check (Step -1):
git fetch, and if the clone is behind upstream, offer to pull before re-capturing - a re-run is exactly when renderer/caption improvements should land. Never pull silently; offline → skip and continue. - Auth still alive? If the flow uses a
profile, verify the saved session headlessly (load the flow's URL, screenshot, look for a login wall). Dead session → have the user runnpm run login -- <profile> <url>before proceeding. - Codebase available? If the app's repo is accessible, read the diff since the last capture (the previous render's timestamp is your anchor). It usually names the changed surfaces and broken selectors up front - tell the user which scenes you expect to be affected before spending a capture run.
- State reset: if
reset.mjsexists, it runs first. If the flow mutates state and there is no reset recipe, stop and write one (per the main playbook).
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.
- 10d ago First seen · 33 lines · 80 tokens per session scan A 5ffb8fc6f238
ultrademo-rerun is a skill published in the GitHub repository new-xp/ultrademo (26 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 932 once invoked, about $0.0004 per session on Opus 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 skills, from other repositories
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
render-cosmic-mythology-voiceover
Assemble a cosmic-mythology-voiceover reel from a config — a warm spoken voiceover carries the whole narrative while N curated cosmic stills are weighted beat-synced across the delivered VO duration (cutdur = VOdur times weight over the weight sum, so emotional beats hold longer), Ken-Burns-zoomed per still (scale 2x…