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/takaoumehara/superforge-skill/superforge-scrollnpx skills add takaoumehara/superforge-skill --skill superforge-scrollgit clone --depth 1 https://github.com/takaoumehara/superforge-skillWrote 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/takaoumehara/superforge-skill/superforge-scroll)<a href="https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-scroll"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-scroll.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 5.1 | $0.00241 | $0.08516 |
| Opus 5 | $0.00120 | $0.04258 |
| Sonnet 5 | $0.00048 | $0.01703 |
| Haiku 4.5 | $0.00024 | $0.00852 |
Grade A, and why
superforge-scroll 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 — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superforge Scroll — Cinematic Scroll-Scrubbed Worlds
A landing page where scroll drives a camera. It flies through a space — into a building, along a route, across a miniature world — continuously, with no visible cuts. The visuals are pre-rendered AI video; the page just scrubs them by scroll position. This is the technique behind Apple's scroll-through product pages: the camera genuinely moved, scroll only drives time.
What gets produced: a camera plan → N scene stills → N legs → (architecture B only) N−1 connectors → a self-contained scrub engine that plays the chain as one flight.
Three things distinguish a build that works from one that merely renders:
- The camera is planned before any pixel exists. The still is not a picture of the
scene, it is the camera's frame 0. Skip the plan and you are asking a model to invent
routes between six unrelated viewpoints. → §2,
references/planning.md - Seams must be frame-identical. Every chained clip starts from the actual rendered last frame of the previous one, never from a fresh render of the same subject. → §6
- The backend must be probed, not trusted. A video API can accept your image, ignore
your prompt, bill you, and return a frame-locked clip flying the wrong way. → §4,
references/providers.md
The scrub engine is self-contained vanilla JS — it builds its own DOM and injects its own CSS into a container you give it — so it drops into plain HTML, Next.js, Vue, Rails, anything. Do not assume a framework. The value here is the plan, the seam method, and the backend contract, not the frontend.
1. Interview — ask what you cannot sensibly default
The subject is the user's to state. Ask it as an open question in plain prose, never a fabricated multiple-choice list of industries — a made-up list biases them and reads as you deciding their business for them. Reserve structured choices for the genuinely enumerable, lower-stakes decisions, and signal that "other" is available.
What ships with it
13 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.
- assets/templates/scroll-world.md 5.2 KB
- evals/evals.json 4.3 KB
- NOTICE.md 1.8 KB
- README.ja.md 7.7 KB
- README.md 6.1 KB
- references/index-template.html 2.6 KB
- references/knockout.py 2.8 KB runs code
- references/pipeline.md 10 KB
- references/planning.md 20 KB
- references/prompts.md 10 KB
- references/providers.md 15 KB
- references/scrub-engine.js 28 KB runs code
- scripts/plan_map.py 19 KB runs code
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 · 599 lines · 241 tokens per session scan A 37e936412780
superforge-scroll is a skill published in the GitHub repository takaoumehara/superforge-skill (1 stars, last pushed 21d ago), licensed MIT. It adds 241 tokens to every session and 8,516 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 2026-08-31.
Other skills, from other repositories
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
mongodb-query-optimizer
Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
lov-article-creator
统一创建、改写、品牌化或忠实转载微信公众号文章包:正文写作调用唯一文风与作者性能力,离线完成结构、品牌、封面、4:3 首图、来源与质量验收。Use when asked to write, brand, audit, or faithfully repost a WeChat article package.
lov-env-management
统一管理平台、账号与多组 API Key,维护有效期和启用状态,安全同步到 zsh 或用户会话环境,并提供脱敏 Dashboard;用户说“管理环境变量”“rotate API keys”时使用。.