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 ssmurfgg04-gif/context-m --skill video-shortformgit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/video-shortform)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/video-shortform"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/video-shortform/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/ssmurfgg04-gif/context-m/video-shortform"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/video-shortform.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 | $0.00110 | $0.02933 |
| Opus 5 | $0.00055 | $0.01466 |
| Sonnet 5 | $0.00022 | $0.00587 |
| Haiku 4.5 | $0.00011 | $0.00293 |
Grade A, and why
video-shortform scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **User wants offline / self-contained** → `curl -L -o sample.mp4 <hotlink>` into the case folder, then `<video src="sample.mp4">` This is a copy
100% identical to video-shortform — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Shortform Template
Camera-HUD mockup that wraps a real piece of footage with pro-camera (RED / ARRI / Blackmagic / Sony Cine-flavored) viewfinder chrome and lets the user audition 8 film-emulation looks against it.
This template is not a TikTok / Reels / 视频号 / 抖音 social mockup, not a storyboard, not a shot list, not a 分镜 / 脚本 document, not a vertical-video ad poster.
⚠️ Three Pre-flight Gates — clear all three BEFORE writing code
Gate 1 — Is this actually a HUD job, or a script/storyboard job?
Trigger words that mean this skill is wrong and you should refuse:
| User says | What they actually want | Correct response |
|---|---|---|
| 短视频脚本 / 视频脚本 / script doc | shot-by-shot text with VO / timing | refuse, suggest a doc template or wireframe-sketch |
| 分镜 / storyboard / shot list | frame-by-frame thumbnails + descriptions | refuse, suggest a storyboard layout |
| 短视频封面 / 视频封面 / video cover | static image / social card | refuse, suggest social-card-* skills |
| 视频号/抖音/小红书视频卡 | feed-style mockup with profile/likes/comments | refuse, suggest a social card |
| 视频海报 / video poster | static print-style poster | refuse, suggest social-card-image-led |
| 调色 demo / LUT 预览 / 滤镜对比 / cinematographer portfolio / camera-app demo / 拍摄取景器 / viewfinder | ✅ this is the right skill | proceed |
If the user's words straddle "脚本 / 拍摄 HUD" ambiguity, stop and ask:
"你要的是 (a) 拍摄取景器 HUD wrap 一段真视频做调色/镜头展示,还是 (b) 视频脚本/分镜的文档?这个 skill 只做 (a),(b) 我会换别的 skill 来做。"
Don't guess. Wrong skill = full rewrite.
Gate 2 — Where is the video coming from?
The chrome wraps a real <video>. A <div> with [视频画面] text inside is not acceptable — that's what B48 did and the whole point of this template was lost.
Decision tree:
- User gave a video file / URL → use it directly in
<video src="..."> - User gave nothing but is OK with sample footage → pick ONE from the Hotlink List below, paste the URL into
<video src>, add a one-liner "示例素材:Big Buck Bunny / 公共测试视频,替换为自己的素材后效果一致" - User wants offline / self-contained →
curl -L -o sample.mp4 <hotlink>into the case folder, then<video src="sample.mp4"> - Unclear → stop and ask which of 1/2/3 they want
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.
- 9d ago First seen · 198 lines · 110 tokens per session scan A 649cc96966e0
video-shortform is a skill published in the GitHub repository ssmurfgg04-gif/context-m (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 110 tokens to every session and 2,933 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to video-shortform, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ai-style
A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.
data_analysis
A data-analysis guide for doing mathematical calculations and descriptive statistics with confirmed, sourced data. Descriptive statistics summarise data using measures such as totals, averages, or ranges.
gsd-sketch
Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode).
design-an-interface
Produce 3+ radically different designs for a module, API, or interface, compare them in prose, and synthesize a recommendation. Use when asked to "design an interface", "shape this API", "design it twice", "explore module boundaries", or when planning a new deep module and the first idea is unlikely to be the best.…
01-plan
Turn a request, ticket, or file into a phased implementation plan. Use to plan a feature before building, or to turn a ticket into phases. Do NOT use to write code or review a diff.
impeccable
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for…