Borrowing it
Nothing to install: this file belongs to st0012/cctop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/st0012/cctop/master/.agents/skills/video-storyboard/SKILL.mdgit clone --depth 1 https://github.com/st0012/cctopWrote 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/st0012/cctop/video-storyboard)<a href="https://agentmods.dev/skills/st0012/cctop/video-storyboard"><img src="https://agentmods.dev/badge/skills/st0012/cctop/video-storyboard/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/st0012/cctop/video-storyboard"><img src="https://agentmods.dev/badge/skills/st0012/cctop/video-storyboard.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 | $0.00202 | $0.03329 |
| Opus 5 | $0.00101 | $0.01665 |
| Sonnet 5 | $0.00040 | $0.00666 |
| Haiku 4.5 | $0.00020 | $0.00333 |
Grade A, and why
video-storyboard 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 12d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Storyboard
A repeatable process for the part of a video that decides whether it works: the narrative. Rendering executes the story; this skill designs it.
For cctop launch videos, this is the first half of the workflow:
- Use this skill for story/script/storyboard/audit decisions.
- Render through the repo video pipeline (
cd video && ./build.sh launchfor the launch cut). - After the user approves the rendered video, switch to
$video-assetsand publish with its confirmation gate. That workflow uploadscctop-launch.mp4,cctop-launch-720p.mp4, and a freshly generatedcctop-launch-preview.aviftogether to the non-latestmedia-assetsrelease.
For cctop product facts, audience, feature-fit judgment, and language choices,
read PRODUCT.md before writing positioning or scripts. Use README.md for
current public-facing claims and supported-tool lists.
It has two modes:
- DESIGN — build a video's story from scratch (product facts → approved storyboard).
- AUDIT — run the same lenses over a finished or draft video to find what's weak and how to fix it.
Pick the mode from the request. "Storyboard a video for X" → DESIGN. "Why does this video feel flat / make it better / review this cut" → AUDIT.
Everything here is built from frameworks that survived adversarial fact-checking. The frameworks are solid; many of the numbers floating around the industry are blog-grade rules of thumb. Where a guideline is directional rather than proven, it is marked [directional]. See references/frameworks.md for provenance, citations, and the specifics that were refuted (so you don't codify folklore).
The core idea
Most product videos fail the same way: they are a feature montage from the product's point of view ("here's the panel, here are the tabs, here are the themes"). They list capabilities instead of telling the story of a person whose problem gets solved.
The fix is one reframe and four moves:
- The viewer is the hero; the product is the guide. (StoryBrand) The story is about them and their struggle, not about your UI.
- Pick one spine and fill it — don't free-associate beats.
- Connect beats by cause-and-effect (but/therefore), never by chronology (and then).
- Engineer the opening for a muted, scrolling viewer — the first frame must earn the next two seconds.
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.
- 12d ago First seen · 132 lines · 202 tokens per session scan A 008ed750b3d5
video-storyboard is a skill published in the GitHub repository st0012/cctop (150 stars, last pushed 5d ago), licensed MIT. It adds 202 tokens to every session and 3,329 once invoked, about $0.0010 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
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
agf
Find local coding-agent sessions, inspect bounded metadata or summaries, and prepare a read-only resume plan with AGF. Use for finding prior work across agent CLIs, not for executing agents, deleting sessions, or reading full transcripts.
dropover
Configure Dropover file-shelf workflows and URL integrations, and diagnose macOS gesture or window behavior.
progress
Use before starting or writing anything that will take more than about half a minute — a build, a test suite, a lint pass, a data import, a migration, a batch job, a deploy, a video encode, a long fetch loop, a script whose one job is to run one of those — so that the person who started it can watch it get there…
sq-do-not-disturb
Do Not Disturb mode — pause quests for 2 hours. Use this when the user says 'stop showing me stuff', 'too many quests', 'quest fatigue', 'these are annoying', 'I'm getting too many notifications', 'not now', 'leave me alone', 'stop interrupting', 'I need a break', 'pause quests for a bit', 'quiet mode', 'mute…
sq-settings
Enable or disable SideQuest quests. Use this when the user says 'turn off quests', 'stop sidequest', 'enable sidequest', 'disable the plugin', 'turn off the plugin', 'disable quests', 'stop showing quests', 'I want to pause quests permanently', 'disable the sidequest plugin', or similar requests to permanently toggle…