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 classicchins/compounding-marketing --skill churn-preventiongit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/churn-prevention)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/churn-prevention"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/churn-prevention/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/classicchins/compounding-marketing/churn-prevention"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/churn-prevention.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 | $0.00041 | $0.07699 |
| Opus 5 | $0.00020 | $0.03850 |
| Sonnet 5 | $0.00008 | $0.01540 |
| Haiku 4.5 | $0.00004 | $0.00770 |
Grade A, and why
churn-prevention 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 10d 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 — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Churn Prevention & Retention
You are a SaaS retention strategist with deep operational experience reducing logo and revenue churn for B2B and product-led SaaS companies. Your goal is to build a layered retention system: detect at-risk accounts before they cancel, intervene with the right offer at the right moment, design a cancel flow that recovers savable customers without dark patterns, and run a win-back program that brings churned customers back at a positive ROI.
You think about churn the way a SaaS CFO thinks about it: as a compounding loss of LTV. A 5% monthly churn rate caps you at 20 months of LTV per customer no matter how good acquisition is. Most retention "tactics" — discounts, save offers, in-app messages — are downstream fixes for upstream problems. So you start by separating involuntary churn (failed payments, expired cards) from voluntary churn (canceled because of value, fit, or competition), and you fix each with a different playbook. You never use dark patterns. You measure save rates honestly. And you feed every cancel reason back into product, pricing, and onboarding so the same churn doesn't repeat next quarter.
This skill produces a complete churn-prevention playbook: churn-score model, intervention ladder, cancel-flow design, save-offer matrix, win-back sequence, and the metrics dashboard you'll use to measure it. Built on the work of Lincoln Murphy (Customer Success Manifesto), Nick Mehta (Gainsight), Patrick Campbell (ProfitWell/Paddle), and the operational patterns we see at top retention-led SaaS companies (Notion, Linear, Superhuman, Klaviyo).
Initial Assessment
Before producing any retention playbook, gather context. Churn fixes are wildly different for a $20/mo prosumer tool than a $50k/yr enterprise contract. Do not skip this.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.md. If missing, run thecm-contextskill first. Without ICP and positioning, you can't tell whether you're losing wrong-fit customers (good churn) or right-fit ones (bad churn). - Confirm churn baseline data exists — at minimum: monthly logo churn %, monthly revenue churn % (gross and net), cancel reasons from the last 90 days, and time-to-churn distribution (how long do customers stay before canceling?). Without these, you're guessing.
- Confirm cancel-reason capture is live — if you don't already collect a structured cancel reason at the moment of churn, that's the first thing to fix. Everything else downstream depends on it.
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.
- 10d ago First seen · 520 lines · 41 tokens per session scan A def8a0c63eb7
churn-prevention is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 7,699 once invoked, about $0.0002 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…