viral-loops

viral-loops is a skill for Claude Code from ranjeeetvimal/growth-skills. It costs 121 tokens per session (860 once invoked), scanned A, original, MIT.

A growth-planning skill for designing customer-sharing loops, first-use activation, and repeat use as measurable experiments. A viral loop is a cycle where existing users help bring in new users.

In plain words
What is it for?
Use it to choose suitable growth loops, calculate their expected sharing rate, plan onboarding step by step, and define retention messages and triggers. It also covers the path from free use to paid use.
Why use it?
It separates genuine user-driven growth from plans that merely reduce customer-acquisition costs. It also connects attracting users with getting them to value quickly and giving them reasons to return.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the plg-architect plugin — 7 skills shipped together

Good fit Use it to choose suitable growth loops, calculate their expected sharing rate, plan onboarding step by step, and define retention messages and triggers. It also covers the path from free use to paid use.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ranjeeetvimal/growth-skills/viral-loops
Install

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.

Any agent
npx skills add ranjeeetvimal/growth-skills --skill viral-loops
Clone the repo
git clone --depth 1 https://github.com/ranjeeetvimal/growth-skills

Made for: Claude Code.

Or install plg-architect, the plugin that ships this one along with the rest of its 7 skills.

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.

agentmods badge for viral-loops

README.md
[![agentmods](https://agentmods.dev/badge/skills/ranjeeetvimal/growth-skills/viral-loops/github.svg)](https://agentmods.dev/skills/ranjeeetvimal/growth-skills/viral-loops)
Your own site
<a href="https://agentmods.dev/skills/ranjeeetvimal/growth-skills/viral-loops"><img src="https://agentmods.dev/badge/skills/ranjeeetvimal/growth-skills/viral-loops/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.

agentmods 80×15 button for viral-loops

Your own site · 80×15
<a href="https://agentmods.dev/skills/ranjeeetvimal/growth-skills/viral-loops"><img src="https://agentmods.dev/badge/skills/ranjeeetvimal/growth-skills/viral-loops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 860 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.00860
Opus 5 $0.00060 $0.00430
Sonnet 5 $0.00024 $0.00172
Haiku 4.5 $0.00012 $0.00086

Measured 11d ago against content hash 417ff9497da6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

viral-loops 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 11d 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.

PLG-Architect/skills/viral-loops/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Viral Loops, Activation & Retention — Bet-First

You are a growth engineer who knows most "viral strategies" fail — and who still finds the one real loop a product has, makes it buildable, gets users to value fast, and keeps them coming back. Acquisition without retention is a leaky bucket; you design all three.

Reference library (read on demand)

  • references/loop-patterns.md — the loop-type menu with honest K ranges, K-factor math, the activation levers (aha/TTV/onboarding), the retention levers, and free-to-paid.
  • For deeper pricing/monetization strategy, defer to plg-strategy — cover free-to-paid mechanics here.

Start: read context, then design

Read .claude/founder-context.md and .claude/strategy-snapshot.md (obey its principles). Match the product to the loop menu yourself — propose the 1-2 loops that fit and say why the others don't.

Rules

  1. Elaborate — don't summarize. The loop is a buildable spec (mechanic, exact copy/surface, K math shown, instrumentation). The activation sequence is written step by step (screen by screen). The retention playbook names concrete mechanics with the actual message/trigger. One-liners are a failure.
  2. Connected + self-contained. Build on the strategy; show the math; write like an engineer's brief. If K < 1, call it a CAC amplifier plainly. Confidence tags throughout.

Process

  1. Reality check — real viral mechanic, or is growth content/SEO/paid? Say it straight.
  2. Pick 1-2 loops — the specific mechanic for THIS product, elaborated, with K math + instrumentation.
  3. Activation sequence — the aha named precisely, the TTV target, the onboarding step by step.
  4. Retention playbook — the weekly value receipt, the Day 3/7/30 re-engagement ladder, the habit anchor, status/telemetry, and community. Name the ONE lever with the most leverage and elaborate it.
  5. Free-to-paid — the paywall lever, expected impact, the A/B test.

Output format

Open with the real headline (the one loop that's available, or the honest "this won't go viral"). Then, as connected sections:

  1. 1-2 loop bets — elaborated mechanic + K math + instrumentation + 30-day validation.
  2. Activation sequence — aha, TTV target, the onboarding steps in order (with the self-test ritual).
  3. Retention playbook — the concrete mechanics, with the actual triggers/messages.
  4. Free-to-paid bet — lever + expected impact + test.
  5. Sacrifices — loops/tactics we're NOT building and why.
  6. Recommendations — a short numbered list of what to build first, in order (acquire → activate → retain).

Read the full file on GitHub · 62 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 62 lines · 121 tokens per session scan A 417ff9497da6

Subscribe to this mod's changes

viral-loops is a skill published in the GitHub repository ranjeeetvimal/growth-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 860 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 2026-08-31.

Related

Other skills, from other repositories

research-seo-demand

A Chinese-language process for researching SEO opportunities, where SEO means improving pages so they can appear in search results. It studies user needs, keyword demand, search-result pages, and competing pages using Bing data.

tsingyuai/growth-lab · 102 tokens

create-seo-page

A Chinese-language workflow for creating and implementing search-focused pages in an existing product repository. SEO means improving a page so it can be found and understood through search engines.

tsingyuai/growth-lab · 93 tokens

review-seo-performance

A review process for evaluating search visibility and AI citations using Bing Webmaster data. It examines whether pages are indexed, how they appear in searches, and when AI-generated answers cite them.

tsingyuai/growth-lab · 85 tokens

xhs-render-cards

A production guide for turning approved Xiaohongshu drafts into reviewable image cards. Xiaohongshu is a social platform where these cards are published, and the guide covers copy, evidence, visual planning, and compliance.

tsingyuai/growth-lab · 89 tokens

run-seo-page-loop

Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review. Use when taking an SEO page from opportunity discovery through publication, measurement, iteration, or continuing a…

tsingyuai/growth-lab · 65 tokens

xiaohongshu-mcp

A browser-based, read-only process for researching posts on Xiaohongshu, a Chinese social platform for user-created lifestyle and product content. It can collect search results, candidate cover images, selected post details, and sanitized evidence.

tsingyuai/growth-lab · 78 tokens