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 tushaarmehtaa/tushar-skills --skill demo-videogit clone --depth 1 https://github.com/tushaarmehtaa/tushar-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/tushaarmehtaa/tushar-skills/demo-video)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/demo-video"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/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/tushaarmehtaa/tushar-skills/demo-video"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/demo-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.01479 |
| Opus 5.5 | $0.00016 | $0.00592 |
| Sonnet 5.5 | $0.00008 | $0.00296 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
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 2mo 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo video
Turn one defensible message into a visual sequence that works in its viewing context, then implement it with the repository's Remotion setup. Story, evidence, and comprehension determine the treatment; transitions do not.
Establish the brief from available evidence
Inspect the product, existing media, brand assets, UI, documentation, and Remotion configuration before asking questions. Establish:
- target viewer and what they know before watching;
- destination, aspect ratio, sound-on or sound-off context, and duration range;
- one primary claim or learning outcome;
- product action, result, data, or demonstration that can prove it;
- call to action or final implication;
- available footage, UI states, narration, music, fonts, and brand constraints;
- deadline, rendering environment, and required deliverables.
Ask only for missing information that changes the claim, evidence, production scope, or rights to use an asset. If creative direction is open, propose a treatment and storyboard rather than asking the user to invent scenes.
Choose the format
- Product walkthrough — chronological task completion with legible UI and minimal editorial interruption.
- Launch or social clip — compressed proposition, product evidence, payoff, and action; must work muted if the destination commonly autoplays without sound.
- Technical explainer — mechanism, observation, interpretation, limitation, and implication. Read explainer writing before scripting.
- Feature demo — one capability, starting state, action, visible result, and boundary.
- Narrated tutorial — paced instruction with prerequisites, cursor intent, captions, recovery, and a reproducible result.
Do not combine every format into one video. When several outputs are requested, define a master narrative and decide which beats survive each cut.
Write a proof-led treatment
Before code, produce:
Viewer:
Destination and format:
Primary claim:
Visible proof:
What must be understood by the end:
Narration/caption approach:
Treatment:
Beat list with approximate timing:
Required assets or captures:
Risks or unknowns:
What ships with it
4 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.
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.
- 2mo ago First seen · 152 lines · 40 tokens per session scan A 260d52b6da4f
demo-video is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (12 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 1,479 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 2026-08-30.
demo-video compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| demo-videotushaarmehtaa/tushar-skills | Skill | 12 | 2d ago | MIT | A | 40 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |