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 beefiker/superloopy --skill superloopy-clonegit clone --depth 1 https://github.com/beefiker/superloopyWrote 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/beefiker/superloopy/superloopy-clone)<a href="https://agentmods.dev/skills/beefiker/superloopy/superloopy-clone"><img src="https://agentmods.dev/badge/skills/beefiker/superloopy/superloopy-clone/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/beefiker/superloopy/superloopy-clone"><img src="https://agentmods.dev/badge/skills/beefiker/superloopy/superloopy-clone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 25 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00113 | $0.04420 |
| Opus 5.5 | $0.00045 | $0.01768 |
| Sonnet 5.5 | $0.00023 | $0.00884 |
| Haiku 4.5 | $0.00011 | $0.00442 |
Grade A, and why
superloopy-clone 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 14d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superloopy Clone
Reverse-engineer a target URL into a working local implementation with audit artifacts. Use this only for authorized cloning, migration, learning, or recovery work. Do not help with phishing, deceptive impersonation, credential capture, or evading a site's terms.
When multiple URLs are provided, process each host independently. Keep every site's research, screenshots, assets, and evidence isolated under paths like docs/research/<hostname>/, docs/design-references/<hostname>/, and .superloopy/evidence/website-clone/<hostname>/.
This is not "inspect once, then redraw." Act as the foreman: inspect one section, write the exact spec, dispatch or build that bounded slice, then keep extracting the next section while builders run. A hard section is where extraction gets stricter, not where approximation becomes acceptable.
Reference Example
Transferloom.com is a reference result for this workflow: superloopy-clone reproduced the page locally and passed desktop/mobile browser validation with preserved sticky navigation, animated hero, app preview sections, comparison table, security panel, sister app banner, footer, local assets, and a Superloopy evidence trail.
Use that bar for completion claims. A clone is successful only when it has this shape of evidence: source screenshots, research notes, component specs, downloaded assets, local browser screenshots, validation output, visual QA notes, and a final evidence artifact.
Superloopy Contract
- Create or reuse a Superloopy plan. Use an evidence root like
.superloopy/evidence/website-clone/<hostname>/. - Preserve extraction artifacts: screenshots, topology, behavior notes, component specs, asset inventory, validation output, and visual QA notes.
- Record final proof with
SUPERLOOPY_EVIDENCE: <path-under-active-evidence-root>when a worker is involved, orsuperloopy loop evidencewhen recording from the parent. - Do not add dependencies without asking. If a clone needs a package for parity, explain why and get approval first.
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.
- 14d ago Changed a9f801e16f7d
- 1mo ago First seen · 306 lines · 113 tokens per session scan A 87ab98550ed0
superloopy-clone is a skill published in the GitHub repository beefiker/superloopy (112 stars, last pushed 13d ago), licensed MIT. It adds 113 tokens to every session and 4,420 once invoked, about $0.0005 per session on Opus 5.5. 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
heang-world
An optional web design module for adding complete visual themes, called worlds, and animated transitions between them. It keeps the page's content and layout while changing its styling, background, and optional visual objects.
maestro-design
Use when creating UI components, pages, design systems, or converting Figma/mockups to code. Covers Tailwind + shadcn/ui + Radix primitives, design tokens, responsive, a11y (WCAG 2.2), motion, and Figma→code workflow. Use for scaffolding a design system or generating production-ready UI. Triggers: figma, tailwind…
heang-design
A design system for building websites and app interfaces in a specific visual style. It supplies shared visual rules, components, motion, and optional 3D elements for projects associated with the named designer and products.
genudo-design-system
Canonical visual styling, color tokens, typography rules, component geometry, and dashboard hierarchy for GenuDo web dashboards, UI widgets, and mobile surfaces (based on the GenuDo Handover Specification). Use whenever designing, generating, or restyling any GenuDo dashboard, frontend component, or report.
compose-creative-ui
A workflow for combining visual interface components and effects in an existing frontend while preserving its current design system and product identity. It covers component sources such as shadcn/ui, Magic UI, Radix, React Bits, and related tools.
implement-ui-motion
A workflow for implementing motion and micro-interactions in an existing frontend. It covers CSS, the Web Animations API, View Transition API, Anime.js, Motion, and GSAP, including reduced-motion support.