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 agentmods add commands/maigentic/stratarts/retention-optimization-expertgit clone --depth 1 https://github.com/maigentic/stratartsWrote 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/commands/maigentic/stratarts/retention-optimization-expert)<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>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 | $0.00045 | $0.08972 |
| Opus 5 | $0.00023 | $0.04486 |
| Sonnet 5 | $0.00009 | $0.01794 |
| Haiku 4.5 | $0.00005 | $0.00897 |
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.
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
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.
- 4d ago First seen · 817 lines · 45 tokens per session scan A a5e60a5526a9
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.
Other commands, from other repositories
doctor
Health check for greatcto. Shows pipeline state, missing artefacts, hook status, last run per agent, and permission-denied tail.
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
resume
Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.
ccr
CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.
coding-audit
Medical-coding / revenue-cycle compliance audit. Invokes rcm-reviewer to assess autonomous ICD-10-CM / CPT / HCPCS coding for False Claims Act exposure (upcoding/unbundling), NCCI edits + MUEs, medical necessity (LCD/NCD), modifier discipline, HIPAA minimum-necessary — and force a certified-coder (CPC/CCS) sign-off.
tax-review
Tax-filing compliance check — invokes tax-reviewer to produce TM-tax-{slug}.md with MeF e-file schema, Form 8879, PTIN/Circular 230, and IRC §7216 consent gaps.