customer-retention-engine

customer-retention-engine is a skill for Claude Code, Codex from finsilabs/awesome-ecommerce-skills. It costs 24 tokens per session (2,300 once invoked), scanned B, original, MIT.

A set of workflows for contacting customers whose purchases or engagement are declining before they stop buying. It uses behavior such as fewer orders, smaller orders, or browsing without purchasing to trigger follow-up campaigns.

In plain words
What is it for?
Use it to create post-purchase follow-ups, targeted offers, and campaigns for at-risk customers. It also helps decide who needs an incentive and who is likely to buy again without one.
Why use it?
It helps stores spot likely churn early and respond before customers become inactive. This avoids treating every customer the same or waiting until a customer has already left.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Codex; mentions Gemini CLI.

Good fit Use it to create post-purchase follow-ups, targeted offers, and campaigns for at-risk customers. It also helps decide who needs an incentive and who is likely to buy again without one.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine
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 finsilabs/awesome-ecommerce-skills --skill customer-retention-engine
Clone the repo
git clone --depth 1 https://github.com/finsilabs/awesome-ecommerce-skills

Made for: Claude Code, Codex.

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 customer-retention-engine

README.md
[![agentmods](https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine/github.svg)](https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine)
Your own site
<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine/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 customer-retention-engine

Your own site · 80×15
<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,300 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00024 $0.02300
Opus 5 $0.00012 $0.01150
Sonnet 5 $0.00005 $0.00460
Haiku 4.5 $0.00002 $0.00230

Measured 9d ago against content hash 83020f8ac6a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

customer-retention-engine scanned grade B with 1 finding 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

await fetch('https://a.klaviyo.com/api/events/', { method: 'POST',
skills/marketing-growth/customer-retention-engine/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Customer Retention Engine

Overview

Acquiring a new customer costs 5–7x more than retaining an existing one. A retention engine identifies customers who show declining engagement — reduced purchase frequency, decreasing order values, browsing without buying — and intervenes with personalized campaigns before they lapse. Klaviyo and AutomateWoo can build these workflows with no custom code using predictive analytics built into the platform.

Note: For reactivating already-lapsed customers, see @win-back-reactivation. This skill focuses on proactive churn prevention before customers lapse.

When to Use This Skill

  • When repeat purchase rate is declining month-over-month
  • When a significant percentage of customers only ever purchase once
  • When you want to proactively contact customers before they go fully dormant
  • When building a post-purchase nurture program beyond the first 30 days
  • When needing to identify which customers are worth offering a discount vs. which will repurchase anyway

Core Instructions

Step 1: Choose the right tool for your platform

Platform Recommended Tool Why
Shopify Klaviyo Klaviyo's predictive analytics automatically calculates expected next purchase date and churn risk for every customer; no manual scoring needed
WooCommerce AutomateWoo ($99/yr) Deep WooCommerce integration, "Customer win-back" workflow type, RFM segmentation built in
BigCommerce Klaviyo or Omnisend Both integrate natively with BigCommerce order events and offer predictive churn scoring
Custom / Headless Klaviyo (via API) Send order events to Klaviyo; use their predictive analytics to identify at-risk customers

Step 2: Define your churn threshold

Churn timing depends on your product's natural repurchase cycle:

Product Category Expected Repurchase Cycle At-Risk Threshold Churned Threshold
Consumables (skincare, supplements) 30–60 days 60+ days since last order 120+ days
Apparel/fashion 60–90 days 90+ days 180+ days
Home goods 90–180 days 180+ days 365+ days
Electronics accessories 120–365 days 180+ days 365+ days

Read the full file on GitHub · 199 lines

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. 9d ago First seen · 199 lines · 24 tokens per session scan B 83020f8ac6a9

Subscribe to this mod's changes

customer-retention-engine is a skill published in the GitHub repository finsilabs/awesome-ecommerce-skills (52 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 2,300 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.