Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mrieck/demoday-claude-pluginnpx agentmods add skills/mrieck/demoday-claude-plugin/demo-shortsWrote 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/mrieck/demoday-claude-plugin/demo-shorts)<a href="https://agentmods.dev/skills/mrieck/demoday-claude-plugin/demo-shorts"><img src="https://agentmods.dev/badge/skills/mrieck/demoday-claude-plugin/demo-shorts/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/mrieck/demoday-claude-plugin/demo-shorts"><img src="https://agentmods.dev/badge/skills/mrieck/demoday-claude-plugin/demo-shorts.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 | $0.00106 | $0.05087 |
| Opus 5 | $0.00053 | $0.02544 |
| Sonnet 5 | $0.00021 | $0.01017 |
| Haiku 4.5 | $0.00011 | $0.00509 |
Grade A, and why
demo-shorts 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 7d 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cutting a vertical Short
A Short is not a re-render of the demo at a different size. It is its own
15–45 second video cut from the demo project's assets. Work inside the same
project directory as the main demo: the Short lives in a sibling manifest
(shorts.json) that shares the project's clips, audio, cache and Remotion app.
1. Pick a style first
Everything else follows from this. Show the user the four looks and ask which their video is most like:
| style | feels like | mechanics |
|---|---|---|
listicle |
"5 plugins that fix your CSS" — numbered rundown, a cut every ~1.5s | beat engine: face/screen/split/insert windows, #N stamps, boxed captions |
cohost |
screenshare with a person talking below the demo throughout | split framing, steady scene-length pacing, karaoke captions |
flashcard |
text asks, UI answers — big typographic cards alternating with full-bleed clips, no face | beat engine: insert(title)/screen windows, boxed captions |
glide |
one immersive screen recording, the camera gliding to each click | pan framing, karaoke captions |
node scripts/plan.mjs --project demo/<slug> --init \
--manifest shorts.json --from demo.json --style listicle
--style sets the format (1080×1920), presenter mode, caption style and
transition policy, and records style in the manifest. --from demo.json
copies product, brand, voice and presenter identity. The timeline starts empty.
Prefix every scene id with s- — both manifests share clips/ and
assets/, and generated artifacts are named after scene ids.
What is reused vs regenerated
| Asset | Verdict | Why |
|---|---|---|
| Screen captures + event logs | reused, free | Reframed (pan/split/beats) inside the 9:16 frame |
| Voice (designed voiceId) | reused, free | Copied by --init --from |
| Narration lines kept verbatim | reused, free | Same text + voice = cache hit |
| New narration lines | cents | Normal TTS pricing |
| B-roll | regenerated | Stills generate at 9:16; i2v inherits the aspect |
| Presenter clips (full scenes, split bottoms, face beats) | generated per scene | Animated to that scene's narration; billed avatar-seconds, shown in the estimate |
| Cards / captions / bullets / title inserts | free | Rendered, not generated |
Insert stills from a prompt |
~$0.05 each | Beats with an existing image are free |
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.
- 7d ago Changed · +78 lines 06ef4c02eafa
- 11d ago First seen · 268 lines · 106 tokens per session scan A 6a58873e2ad2
demo-shorts is a skill published in the GitHub repository mrieck/demoday-claude-plugin (3 stars, last pushed 7d ago), licensed MIT. It adds 106 tokens to every session and 5,087 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
video-content
Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a…
visual-content
Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals…
compose-creative
Core creative engine — turns a calendar post into finished images or video using 4 modes (anchor-compose, enhance-extend, style-referenced, pure-creative) with brand assets, AI generation, and human approval before credits are spent. Triggers on "/compose-creative", "generate the creative", "make the image for P07"…
c2pa-sign
Embed C2PA provenance manifests in AI-generated assets — the machine-readable AI disclosure EU AI Act Article 50 expects (enforceable since 2 Aug 2026), plus the human-approval record for the Article 50(4) exemption. Triggers on "/c2pa-sign", "sign this asset", "provenance", "content credentials", "AI disclosure"…
full-pipeline
Run the complete production pipeline end to end — parse the calendar, match assets, compose creative, adapt copy, build previews, run reviews, finalize delivery — with checkpoints between phases. Triggers on "/full-pipeline", "run the whole month", "produce the month", "end to end", "do everything", "full production…