retention-optimization-expert

retention-optimization-expert is a command for coding agents from maigentic/stratarts. It costs 45 tokens per session (8,972 once invoked), scanned A, original, MIT.

A retention analysis and planning command for products or services. Retention means keeping users over time; the command examines groups of users, churn, user health, and people at risk of leaving.

In plain words
What is it for?
Use it to analyze user groups and retention curves, identify at-risk users, plan win-back campaigns, suggest product improvements, and create HTML reports with a 90-day roadmap.
Why use it?
It brings together the information needed to understand why users stop returning and which users may leave next. It also turns that analysis into campaigns and an implementation plan.

Command

Part of the stratarts plugin — 27 commands shipped together

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.

agentmods
npx agentmods add commands/maigentic/stratarts/retention-optimization-expert
Clone the repo
git clone --depth 1 https://github.com/maigentic/stratarts

Or install stratarts, the plugin that ships this one along with the rest of its 27 commands.

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 retention-optimization-expert

README.md
[![agentmods](https://agentmods.dev/badge/commands/maigentic/stratarts/retention-optimization-expert.svg)](https://agentmods.dev/commands/maigentic/stratarts/retention-optimization-expert)
Your own site
<a href="https://agentmods.dev/commands/maigentic/stratarts/retention-optimization-expert"><img src="https://agentmods.dev/badge/commands/maigentic/stratarts/retention-optimization-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,972 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.08972
Opus 5 $0.00023 $0.04486
Sonnet 5 $0.00009 $0.01794
Haiku 4.5 $0.00005 $0.00897

Measured 4d ago against content hash a5e60a5526a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

retention-optimization-expert 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 4d 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.

stratarts/commands/retention-optimization-expert.md · 817 lines

How it starts

The opening of the file, as written. The whole thing — 817 lines — stays where its author put it; the contents beside it link to each section on GitHub.

retention-optimization-expert

Mission: Reduce churn and improve retention through cohort analysis, at-risk user identification, win-back campaigns, product improvements, and customer success strategies. Turn one-time users into lifelong customers.


STEP 0: Pre-Generation Verification

Before generating the HTML output, verify all required data is collected:

Header & Score Banner

  • {{BUSINESS_NAME}} - Company/product name
  • {{DATE}} - Report generation date
  • {{D30_RETENTION}} - 30-day retention rate (e.g., "38%")
  • {{D7_RETENTION}} - 7-day retention rate (e.g., "52%")
  • {{CHURN_RATE}} - Monthly churn rate (e.g., "6.2%")
  • {{AT_RISK_PERCENT}} - Percentage of at-risk users (e.g., "18%")
  • {{HEALTH_GREEN}} - Percentage of healthy users (e.g., "62%")
  • {{CURVE_TYPE}} - Short curve type (e.g., "Steep Drop + Plateau")

Executive Summary

  • {{EXECUTIVE_SUMMARY}} - 2-3 paragraphs with retention overview, key interventions
  • {{CURVE_TYPE_FULL}} - Full curve description (e.g., "Steep Drop, Then Plateau (Good)")
  • {{CURVE_DESCRIPTION}} - Explanation of what the curve means for the business

Cohort Analysis

  • {{COHORT_ROWS}} - 4+ cohort rows with M0-M6 retention percentages
    • Each row: cohort name, M0 (100%), M1, M2, M3, M6 with color classes

Segment Retention

  • {{SEGMENT_CARDS}} - 3-4 user segments
    • Each card: segment name, D30 retention, churn rate

At-Risk Identification

  • {{RISK_INDICATORS}} - 4-5 at-risk criteria
    • Each indicator: icon, title, description of criteria

Health Score

  • {{HEALTH_GREEN}} - Healthy percentage (80-100 score)
  • {{HEALTH_YELLOW}} - At-risk percentage (50-79 score)
  • {{HEALTH_RED}} - Churn risk percentage (<50 score)
  • {{HEALTH_FACTORS}} - 5 health score factors with weights

Win-Back Campaign

  • {{WINBACK_TIERS}} - 4 escalating tiers
    • Each tier: name, day range, 2-4 actions

Churn Reasons

  • {{CHURN_ROWS}} - 5-6 churn reasons
    • Each row: reason, percentage, addressable status, action plan

Read the full file on GitHub · 817 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. 4d ago First seen · 817 lines · 45 tokens per session scan A a5e60a5526a9

Subscribe to this mod's changes

retention-optimization-expert is a command published in the GitHub repository maigentic/stratarts (39 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 8,972 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 2026-08-30.