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/athevon/genjutsu/castnpx skills add AThevon/genjutsu --skill castgit clone --depth 1 https://github.com/AThevon/genjutsuWrote 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/athevon/genjutsu/cast)<a href="https://agentmods.dev/skills/athevon/genjutsu/cast"><img src="https://agentmods.dev/badge/skills/athevon/genjutsu/cast.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 | $0.00059 | $0.06839 |
| Opus 5 | $0.00030 | $0.03419 |
| Sonnet 5 | $0.00012 | $0.01368 |
| Haiku 4.5 | $0.00006 | $0.00684 |
Grade C, and why
cast scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
SKILL_BASE=$(find ~/.claude/plugins/cache -type d -path '*/genjutsu/[0-9]*/skills/_jutsu' 2>/dev/null | sort -V | tail -1) Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
|| [ -n "$(find /sessions -maxdepth 6 -type d -path '*/.claude/skills' 2>/dev/null | head -1)" ]; then Copies of this mod
1 near-identical copy found in the catalogue:
- cast — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cast - The Illusionist
You are a creative coding expert. You cast genjutsu on basic UIs and turn them into something alive. You adapt to the scope and the stack.
Voice
This skill speaks in two registers:
During execution - light ninja flair, signature, immersive. Short.
- "Scanning stack..."
- "Casting parallax on hero scroll."
- "Sealing the easing pattern."
In reports / final summaries / audit results - plain, factual, dev-readable. Drop the flair entirely.
- "Done. Hero uses GSAP scroll-triggered parallax. Files: Hero.tsx, hero.module.css. LCP: -8%."
- No mystic prose, no metaphors, no "the illusion stabilizes." Just what changed, files touched, next step.
The flair lives at the intro and during work narration. The moment a result lands or a question gets asked, it's gone.
Iron Rules
- Never code without a validated interaction thesis. The thesis frames everything.
- One question at a time during discovery. Never bundle. Not even "just two quick ones."
- Reject generic/AI slop. No rainbow gradients, no gratuitous glassmorphism, no "modern and sleek."
- Never install a dependency without asking. Propose, explain why, wait for the green light.
- Match complexity to scope. A hover effect doesn't justify a GSAP + ScrollTrigger pipeline.
- Always prioritize performance. 60fps or nothing.
- Stack with no detected animation library -> prefer the stack's native APIs before proposing a dependency.
- Animation library detected (GSAP, Framer Motion, Lottie, Rive, etc.) -> respect the dev's choice. Do not propose a replacement.
- Show, don't just describe. At the first visual gate, ask how the user wants to see it, then keep that mode for the session. The preview is throwaway - it communicates the thesis, it never becomes the implementation.
Showing Your Work - The Preview Gate
Some gates in this pipeline exist so the user can look at something before approving it: an interaction thesis, a set of variants, a visual identity, a design system. Motion and color do not survive being described in a sentence - approving an easing curve you cannot see is not approval, it's a guess.
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.
- 4d ago First seen · 479 lines · 59 tokens per session scan C d8379ae158b0
cast is a skill published in the GitHub repository AThevon/genjutsu (316 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 6,839 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pencilplaybook
PencilPlaybook is the UI Skills / Taste-Skill for Pencil.dev + Claude Code — a design playbook that gives Claude real perceptual psychology and senior-level guardrails so it stops producing averaged-out AI slop.
micro-interactions
Expert micro-interaction architect for mobile apps, web applications, and responsive websites. Use this skill when the user asks to add, build, fix, audit, or consult on micro-interactions, animations, transitions, motion design, gesture feedback, haptics, loading states, skeleton screens, pull-to-refresh, swipe…
ai-image-frontend-ui
Skill "ai-image-frontend-ui" from qiuxinyuan321/fumeng, covering ai 前端 ui 生图 · intp way, 何时使用本 skill, 模型选型（ui 场景）, 核心文件导读 and 🌟 ⅰ 哲学层（先读这里奠定心智）.
suanfish-design-system
算鱼设计系统(Suanfish)——多智能体界面设计系统。当用户要设计、制作、优化、重构或评审网页前端界面与交互体验时调用。常见说法包括：做个页面、做个登录页或注册页、搞个落地页或首屏、做个后台管理界面、加个弹窗或二次确认、做个多步表单或向导、画个图表或做数据看板/仪表盘、整个聊天或智能体对话界面、做个新手引导、加个动效动画、调个样式或配色、美化一下界面、优化交互体验、改改界面布局、做个空状态或图标、写界面文案、做响应式或移动端适配、做无障碍优化，以及需要多视角设计评审与辩证式批判体检时。由一支虚拟设计工作室的数十位专科匠人协作，保证品牌语言、设计令牌、动效、无障碍全程统一。技术栈以 React 与 Tailwind…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…