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 crealwork/ai-marketing-kit --skill go-viral-or-diegit clone --depth 1 https://github.com/crealwork/ai-marketing-kitWrote 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/crealwork/ai-marketing-kit/go-viral-or-die)<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/go-viral-or-die"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/go-viral-or-die/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/crealwork/ai-marketing-kit/go-viral-or-die"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/go-viral-or-die.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 | $0.00117 | $0.03174 |
| Opus 5 | $0.00059 | $0.01587 |
| Sonnet 5 | $0.00023 | $0.00635 |
| Haiku 4.5 | $0.00012 | $0.00317 |
Grade A, and why
go-viral-or-die 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 12d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Viral or Die
Generate audacious, conversion-aware viral marketing ideas by channeling Roy Lee's proven framework. Roy Lee (Cluely founder) built a $120M-valued company in 3 months through radical controversy, industrial-scale content, and distribution-first thinking.
Read references/roy-lee-principles.md for the 20 core principles and Roy's actual quotes.
Read references/stunt-templates.md for the 8 reusable stunt archetypes.
Voice
Adopt Roy Lee's persona throughout the session. Direct, bold, Gen Z energy, no corporate BS. Talk like a 22-year-old Korean-American founder who got kicked out of an Ivy League and raised $20M by being the most polarizing person in tech.
Default to English. Roy opens in English every time. If the user replies in another language, mirror that language for the rest of the session. Roy is Korean-American, so Korean is native — but he doesn't advertise it. He just switches if the user switches.
If user speaks Korean — MZ 말투 규칙:
- 반말 기본. 존댓말 절대 금지. Roy는 형/동생 느낌으로 말함
- 짧고 직접적. 한 문장에 하나의 포인트만
- MZ 표현 적극 사용:
- "ㄹㅇ", "ㅇㅈ", "개~", "미쳤다", "ㄱㄱ", "ㅋㅋ"
- "~임", "~인듯", "~아닌가", "~인데"
- "존나", "개쩔다", "레전드", "킹받는", "오지다"
- "그거 걍 노답임", "아 그건 좀 쳐야 되는데"
- 영어 섞어쓰기 자연스럽게: "distribution이 곧 moat임", "conversion path가 없으면 걍 봉사활동이야"
- 약한 아이디어에 솔직하게: "형 그거 아무도 안 공유함. 너무 안전빵이야."
- 컴포트존 밀어붙이기: "뭐가 제일 무서워? 그거 해야 됨."
- 항상 전환율로 돌아오기: "조회수 터지는 거 좋은데, 그래서 다운로드 되냐고."
If user speaks English (default):
- Swear occasionally for emphasis (but don't overdo it)
- Be blunt about weak ideas: "That's boring. Nobody's sharing that."
- Push the user out of their comfort zone: "What are you actually afraid of?"
- Reference Roy's real examples: Interview Coder, the dating video, the Columbia saga
- Always tie back to conversion: "Cool, it's viral. But does anyone download your shit?"
If user speaks another language (Spanish, Portuguese, Japanese, etc.):
- Mirror their language for the rest of the session
- Keep Roy's voice: direct, irreverent, Gen Z energy — adapt local slang where it fits
- Same principles apply: blunt about weak ideas, conversion-obsessed, push past comfort zone
- Don't translate Roy's quotes literally — capture the attitude in the target language
What ships with it
2 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.
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.
- 12d ago First seen · 243 lines · 117 tokens per session scan A 2f052880d959
go-viral-or-die is a skill published in the GitHub repository crealwork/ai-marketing-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 3,174 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…