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 wenhaochai/claude-plugins --skill videogit clone --depth 1 https://github.com/wenhaochai/claude-pluginsWrote 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/wenhaochai/claude-plugins/video)<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/video"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/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/wenhaochai/claude-plugins/video"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/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 | $0.00062 | $0.01221 |
| Opus 5.5 | $0.00025 | $0.00488 |
| Sonnet 5.5 | $0.00012 | $0.00244 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
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 19d 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.
Video
A video of a piece of work runs about a minute and plays as one piece of motion design.
Design
- One continuous piece. Objects carry from scene to scene: a node becomes an agent, agents regroup, a chart grows out of what was on screen. No cuts between static cards and no heading-plus-figure layouts.
- Open on the work itself. The first frame is a cover, the title over the source's key picture, so a feed's thumbnail shows the work. The picture then clears to a blank frame, the mechanism builds in from nothing over the first seconds, and the title stays alone in the clear space above it. Then the title leaves and that picture carries into the first chapter. The opening has no kicker, author or date line, or tagline.
- The camera stays still: motion comes from the objects themselves, and nothing zooms or pans the whole frame.
- The picture carries the story. No text column stays on screen: each statement is one short line placed next to the action it describes, on screen only for that moment, with its key words in the accent. Numbers and names sit on the visuals as direct labels, and the takeaway is the one full sentence, at the end. Every caption and label earns its place: cut any word the picture already says, and cut a beat that repeats one already shown.
- Copy comes from the source. Titles, names and the takeaway are quoted verbatim, the video adds no summary lines of its own, and it never uses the middle dot (U+00B7).
- Give it rhythm: when a beat repeats, play it slowly the first time and quickly after.
- Explain a mechanism at least as clearly as its source by porting the source figure's beats and labels. Where the source shows single runs and their average, so does the video. No formulas on screen: a statement says the rule in words, and its numbers sit on the visuals as labels.
- Introduce every named setup on screen before the scene that uses it, and show every option from one extreme to the other.
- Show every comparison the source supports, each as a race on one clock, and make each result explicit: the winner gets an accent frame and its number, the loser dims, and a ranking closes the set.
- Choose an example where the obvious option loses at least one race. Keep it typical: each option's run is the session closest to its mean over many sessions, and the video states only results that hold on most sessions.
- Full frame at 1920×1080 and 60 fps, in the source's palette and fonts, with light grain added at encoding. Type stays restrained and the same throughout: a few sizes, each kept for one role, semibold only for headings, emphasis by color, no italics. Nothing overlaps: no text on graphics, and a caption or label leaves before the next one enters. Every object stays inside the frame.
- The site's own mark, its logo and name as in the page header, sits small in the bottom-right corner for the whole video, and no other corner carries text such as a URL. A team's work carries no personal name: the corner holds the marks the owner picks for the team, such as its institutions' emblems. Every scene, the opening included, uses the full height and sits centered in the space above the mark.
- Wording and figures follow the
writingplugin:stylefor the prose and theplotskill's rules (skills/plot/SKILL.md) for marks and legends.
What ships with it
1 file 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.
- 19d ago Changed 66fd788c927c
- 21d ago Changed c24bff7edbbc
- 23d ago First seen · 33 lines · 62 tokens per session scan A 2beaeca4358e
video is a skill published in the GitHub repository wenhaochai/claude-plugins (17 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,221 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 2026-09-25.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.