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 scrollmark/socialgpt-mcp --skill going-viralgit clone --depth 1 https://github.com/scrollmark/socialgpt-mcpWrote 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/scrollmark/socialgpt-mcp/going-viral)<a href="https://agentmods.dev/skills/scrollmark/socialgpt-mcp/going-viral"><img src="https://agentmods.dev/badge/skills/scrollmark/socialgpt-mcp/going-viral/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/scrollmark/socialgpt-mcp/going-viral"><img src="https://agentmods.dev/badge/skills/scrollmark/socialgpt-mcp/going-viral.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 | $0.00166 | $0.01669 |
| Opus 5 | $0.00083 | $0.00834 |
| Sonnet 5 | $0.00033 | $0.00334 |
| Haiku 4.5 | $0.00017 | $0.00167 |
Grade A, and why
going-viral 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Going Viral
Virality is closer to a science than a lottery. The creators who hit consistently aren't luckier — they run a loop: study what already works, form a hypothesis about why, test it with one post, and feed the result back in. This skill is that loop, and it's the conductor for the rest of the SocialGPT toolkit — it grounds each stage in your real data and hands the heavy analysis to the specialist skills.
This skill pairs with the SocialGPT MCP server (https://mcp.gpt.social/mcp).
The MCP provides your data; this skill provides the strategy that turns that data
into your next post. The other skills below ship the deterministic analysis.
Better with a connection. If the SocialGPT tools aren't available, this skill still works — it teaches the full playbook. But it's far stronger connected: instead of generic advice it studies your real outliers, your drivers, and your hooks. If you haven't connected an account yet, do it here first: https://gpt.social/integrations/mcp (public/competitor analysis works with no account; your own data needs a connected account).
When to use
Trigger on the broad, upstream strategy asks: "how do I go viral?", "why isn't my content taking off?", "give me a content strategy", "what should I post next?", "how do I grow my account / get more reach?", "build me a repeatable system", "I'm posting a lot and nothing's working."
These sit above the three specialist skills — when the user wants the whole system, start here and route into them. When they ask a narrow question ("what drives my views", "compare me to @rival", "teardown my hooks"), go straight to the matching specialist.
The loop
Five stages. At each one, pull the user's real data with the MCP, apply the referenced playbook file, and hand the deterministic analysis to the specialist skill.
| Stage | What you do | Pull via the MCP | Hand off to |
|---|---|---|---|
| 1. Research outliers | Find creators/formats that go viral repeatedly in or adjacent to the niche; study why. | list_creator_videos(sort="top"), get_creator, list_similar_videos, search_videos; analyze_creator + get_analysis_status for creators not yet in the library |
competitor-gap-analysis |
| 2. Find your own drivers | Isolate what actually predicts this account's views — length, timing, platform, format. | list_videos(sort="top"), get_content_profile, get_account_metrics |
content-performance-audit |
| 3. Study winning hooks & formats | Read what the top posts' openings and pacing do that the flops don't. | get_video_analysis (transcript, hooks, scenes) |
hook-retention-teardown |
| 4. Ideate against the data | Generate many ideas grounded in stages 1–3, then rank and cut hard. | get_content_profile (pillars + voice) + the outputs above |
— (reason it out; see references) |
| 5. Ship one + review | Make and ship one post — one clean hypothesis test — then read the result and update what you believe. | get_post_metrics_history, get_growth_summary, get_account_metrics |
re-run audit / teardown |
What ships with it
18 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.
- references/algorithm-seeding-and-trust.md 3.3 KB
- references/communication-algorithm-triple-f.md 3.5 KB
- references/content-ideation-pipeline.md 3.4 KB
- references/early-engagement-diagnostics.md 3.3 KB
- references/execution-craft-and-nuance.md 3.4 KB
- references/generalist-principle.md 2.9 KB
- references/hook-anatomy.md 4.5 KB
- references/hook-iteration.md 4.0 KB
- references/narrative-tension-and-retention.md 3.5 KB
- references/platform-algorithm-fluency.md 4.4 KB
- references/proven-viral-formats.md 4.7 KB
- references/reverse-engineering-outliers.md 3.6 KB
- references/self-analysis-and-iteration.md 3.3 KB
- references/story-structure-short-form.md 3.2 KB
- references/viral-content-model.md 2.9 KB
- references/viral-format-engineering.md 3.3 KB
- references/viral-mindset-and-myths.md 3.6 KB
- references/viral-performance-drivers.md 3.9 KB
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 · 107 lines · 166 tokens per session scan A 91c69c0d9ca0
going-viral is a skill published in the GitHub repository scrollmark/socialgpt-mcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 166 tokens to every session and 1,669 once invoked, about $0.0008 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
9router-video
Generate videos via 9Router /v1/videos/generations using xAI Grok Imagine (grok-imagine-video). Async job flow - submit, poll requestid until done, download MP4. Use when the user wants to create, generate, or render a video, text-to-video (txt2vid), or image-to-video.
9router-web-fetch
Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
9router-web-search
Web and X search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router-tts
Text-to-speech via 9Router /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Hyperbolic / Inworld voices. Use when the user wants to convert text to speech, generate audio, voiceover, narrate, or read text aloud.
9router
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…