Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/rules/kevin-liu-01/loop/frontend-10x-external-skills)<a href="https://agentmods.dev/rules/kevin-liu-01/loop/frontend-10x-external-skills"><img src="https://agentmods.dev/badge/rules/kevin-liu-01/loop/frontend-10x-external-skills/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/rules/kevin-liu-01/loop/frontend-10x-external-skills"><img src="https://agentmods.dev/badge/rules/kevin-liu-01/loop/frontend-10x-external-skills.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00660 | $0.00660 |
| Opus 5 | $0.00330 | $0.00330 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
frontend-10x-external-skills 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 9d 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.
What it actually says
External Frontend Skill Routing
When frontend work becomes specialized, route to the imported skill that matches the problem instead of giving generic advice.
Preferred routing:
- use
modern-web-designfor broad contemporary design direction - use
motion-framerfor React component motion, layout transitions, menus, overlays, and most UI animation - use
gsap-scrolltriggerfor scrollytelling, pinning, scrubbed sections, and cross-surface choreography - use
react-three-fiberfor React-based 3D scenes - use
threejs-webglfor lower-level or non-React Three.js work - use
web3d-integration-patternswhen multiple motion/3D libraries need to work together coherently - use
rive-interactivefor stateful designer-authored runtime animations - use
lottie-animationsfor After Effects exported motion assets - use
pixijs-2dfor GPU-accelerated 2D graphics and particle layers - use
spline-interactivewhen a visual-editor 3D workflow is the right fit - use
aframe-webxrfor browser VR/AR or WebXR work - use
lightweight-3d-effectswhen decorative depth is enough and a full engine is overkill - use
animejsfor framework-agnostic timeline/SVG animation - use
barba-jsfor multi-page transition systems - use
scroll-reveal-librariesonly for simple reveal-on-scroll work - use
blender-web-pipelineandsubstance-3d-texturingfor 3D asset and material pipelines - use
babylonjs-engineorplaycanvas-enginewhen the work is closer to game-engine style interactive 3D
Routing priorities:
- prefer
motion-framerover ad hoc React animation code - prefer
gsap-scrolltriggerover generic scroll-effect improvisation - prefer
react-three-fiberover low-level Three.js in React unless low-level control is required - prefer
rive-interactiveover Lottie when runtime state and interactivity matter - prefer
lightweight-3d-effectsover full 3D engines when only mild decorative depth is needed
Exceptions:
- do not force imported skills when the existing codebase already standardizes on another well-chosen stack
- do not use
locomotive-scrollas a new default; prefer Lenis unless maintaining existing Locomotive work or explicitly requested - do not use
scroll-reveal-librariesfor brand-defining motion systems
Repo-local mirrored references live in /Users/kevinliu/Downloads/Dedalus/frontend-frontier-pack/third-party-skills/freshtechbro/ and the routing overview lives in /Users/kevinliu/Downloads/Dedalus/frontend-frontier-pack/codex-skill/frontend-frontier/references/external-frontend-skill-map.md.
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.
- 9d ago First seen · 46 lines · 660 tokens per session scan A 7551dddee8c8
frontend-10x-external-skills is a cursor rule published in the GitHub repository Kevin-Liu-01/Loop (18 stars, last pushed 1mo ago), licensed MIT. It adds 660 tokens to every session, about $0.0033 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 cursor rules, from other repositories
hatch3r-design-system-detection
Mandatory detection of existing design tokens, theme primitives, and component library before AI agents author new UI components.
hatch3r-component-conventions
Component structure, styling tokens, loading/error/empty states, form validation timing, and accessible label patterns for Vue, React, and JSX.
reexamine_keyboard
Re-examine keyboard efficiency — skip links, shortcuts, tab order, focus traps.
motion-design
Motion design rules — context-aware animation principles drawn from Emil Kowalski, Jakub Krehel, and Jhey Tompkins. Covers timing, enter/exit recipes, motion gaps, accessibility, performance, and anti-patterns.
66-stack-shadcn
USE WHEN: working with Shadcn UI, Tailwind CSS, Lucide icons, or Sonner toasts.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.