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 agentmods add skills/onewave-ai/open-agent-stack/scroll-storynpx skills add OneWave-AI/open-agent-stack --skill scroll-storygit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/scroll-story)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/scroll-story"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/scroll-story.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01220 |
| Opus 5 | $0.00028 | $0.00610 |
| Sonnet 5 | $0.00011 | $0.00244 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
scroll-story 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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scroll Story
Scroll-driven sections are the highest-impact thing on a marketing page and the easiest to get wrong. Done well, scrolling feels like operating a machine. Done badly, elements pop in late, the pinned section fights the scrollbar, and on a phone it is a broken mess. The difference is almost entirely in the timing and the mobile pass.
The two mechanics
Reveal -- an animation triggered by scroll position, then it plays on its own clock. Use for content arriving: headings, cards, images, stats. Cheap, robust, works everywhere.
Scrub -- an animation whose playhead is scroll position. The user scrubs it forward and backward. Use when the scroll is the interaction: a product rotating, a diagram assembling, a number counting, a phone screen advancing.
Most sections want reveal. Scrub is expensive to build and to run, so spend it on the one or two moments that carry the page.
Workflow
-
Storyboard in words first. For each scene: what the user sees at 0%, at 50%, at 100% of the scroll through it, and how many viewport heights it takes. If that cannot be written in three lines, the scene is doing too much. Cap the whole page at two or three scroll-driven scenes -- past that, the page feels like a hostage situation.
-
Reveals: use the native tool.
IntersectionObserveror CSSanimation-timeline: view()handles reveals with no library and no scroll listener. Trigger when the element is ~15-20% into the viewport, animate once, then unobserve -- content that re-animates every time it scrolls back into view is a widely disliked pattern.const io = new IntersectionObserver((entries) => { for (const e of entries) { if (!e.isIntersecting) continue e.target.dataset.revealed = 'true' // CSS does the animating io.unobserve(e.target) } }, { rootMargin: '0px 0px -15% 0px' })Never animate a reveal from
opacity: 0in CSS that ships before the observer runs -- if the script fails, the content is invisible forever. Gate the hidden state on ajs-enabledclass or start from the visible state and let the observer add motion.
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.
- 5d ago First seen · 69 lines · 57 tokens per session scan A ae7714a49b9c
scroll-story is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 25d ago), licensed MIT. It adds 57 tokens to every session and 1,220 once invoked, about $0.0003 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
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
pretext
Build creative browser demos with DOM-free text layout.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
inspecting-hermes-desktop-dom
Read the live Hermes desktop DOM/CSS over CDP.
impeccable
Frontend design guidance, upstream-maintained (impeccable).
html-email
Send-ready single-file email.