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/nateherkai/scroll-craft/scrollcraftnpx skills add nateherkai/scroll-craft --skill scrollcraftgit clone --depth 1 https://github.com/nateherkai/scroll-craftWhat 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 | $0.00246 | $0.05323 |
| Opus 5 | $0.00123 | $0.02661 |
| Sonnet 5 | $0.00049 | $0.01065 |
| Haiku 4.5 | $0.00025 | $0.00532 |
Grade A, and why
scrollcraft 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 3d 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 — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scrollcraft
Scroll is the only input every visitor already knows how to use. This skill treats it as a timeline: the wheel is a scrubber, the page is a film with real text on top, and each section behaves differently enough that the visitor keeps going to find out what the next one does.
What you produce: an interview brief, a page grammar, a customer-journey map, a feeling curve with one engineered peak, a scroll score, one signature move, generated assets, one real HTML page on a token-driven design floor, and a strip of screenshots proving it holds up at every scroll position.
What this is not
It is not "generate a flythrough and drop text on it." That approach produces
one device applied to a whole page, and every site built that way is
recognisable at a glance: same claymation diorama, same centred copy, same
01 / 06 counter, same "scroll to explore" nudge. Five sections that behave
identically are one section shown five times.
Four rules follow from that, and they are the spine of this skill:
- Variety is the product. A page uses at least four device families and never the same device twice in a row. Read references/devices.md.
- The world is photographic unless the brand is genuinely illustrated. Soft matte low-poly clay diorama is banned as a default. Read references/worlds.md.
- No continuous chain. A single unbroken camera flight is the most expensive and most fragile thing you can build, and it exists only to hide cuts between scenes. Vary the device instead and the cut disappears for free, because the visitor is not watching one film. Chain only when the brief is literally "one continuous journey."
- A different world is not a different page. The device kit varies how a page looks. Structure is a separate axis, and it has to be decided deliberately or every build inherits the same skeleton. The first four builds did exactly that. Read references/uniqueness.md.
What ships with it
21 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.
- CHANGELOG.md 29 KB
- engine/scrollcraft.css 19 KB
- engine/scrollcraft.js 55 KB runs code
- references/assets.md 13 KB
- references/device-diag.html 8.9 KB
- references/devices.md 21 KB
- references/feel.md 13 KB
- references/taste.md 15 KB
- references/template.html 6.3 KB
- references/uniqueness.md 23 KB
- references/verify.md 23 KB
- references/worldflight.md 16 KB
- references/worlds.md 7.9 KB
- scripts/doctor.mjs 7.0 KB runs code
- scripts/encode.sh 3.1 KB runs code
- scripts/kie.mjs 7.6 KB runs code
- scripts/serve.mjs 2.0 KB runs code
- scripts/shoot.mjs 32 KB runs code
- scripts/workspace.mjs 3.6 KB runs code
- scripts/worldflight-assert.mjs 13 KB runs code
- templates/FINGERPRINTS.md 2.3 KB
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.
- 3d ago First seen · 416 lines · 246 tokens per session scan A 7acaec75089f
scrollcraft is a skill published in the GitHub repository nateherkai/scroll-craft (1,393 stars, last pushed 10d ago), licensed MIT. It adds 246 tokens to every session and 5,323 once invoked, about $0.0012 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
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".
core-web-vitals
Optimize Core Web Vitals (LCP, INP, CLS) for better page experience using field and lab evidence. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".
release
Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.
agent-desktop-ffi
C-ABI bindings over agent-desktop's PlatformAdapter. Consumers (Python ctypes, Swift, Node ffi-napi, Go cgo, C++, Ruby fiddle) link libagentdesktopffi.{dylib,so,dll} and call ad functions directly instead of spawning the CLI binary per call. The canonical observe-act workflow is: adinit → adadaptercreate[withsession]…
Accessibility Auditor
Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.
GitHub Hub
Your intelligent GitHub command center -- start here. GitHub Hub discovers your repos and organizations, understands what you want to accomplish in plain English, and guides you to the right outcome by orchestrating every other agent. No commands to memorize. Just talk.