Skip to main content
command CX Codex

monitor-loyalty — Claude Code command: loyalty program insights

monitor-loyalty — a command to evaluate loyalty program health: tracks member engagement, churn risk, and experiment impact. Surfaces at-risk segments and growth opportunities across tiers and regions.

Apache-2.0 ★ 450 updated 2026-04-03

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/monitor-loyalty.md
Open on GitHub

What monitor-loyalty does

The command pulls enrollment, engagement, redemption, and satisfaction data for a specified time window, then diagnoses program state—tier distribution, churn signals, reward liability. It surfaces member segments needing reactivation or upgrade offers, and reviews campaign results with lift metrics and next-test recommendations.

Output includes a KPI dashboard snapshot with trends and drilldowns, a risk and opportunity list mapped to data owners, experiment summaries, and a JSON plan file for audit trail. The command invokes a member insights analyst and loyalty strategist to validate roadmap adjustments and ensure segmentation standards.

When calling, specify the analysis period (7d, 30d, quarter), report depth (summary or full), and optionally breakdowns—tier, cohort, region, or channel. If KPI thresholds breach twice or reward liability spikes, the command triggers escalation and records remediation in the plan.

What it helps with

  • assess loyalty program health against key metrics
  • identify member segments at risk of churn
  • evaluate experiment results and campaign lift
  • generate prioritized action plan to boost engagement
  • track reward liability and program breakage points

Example prompts for the agent

  • Analyze loyalty program for the last 30 days with full detail, broken down by tier and region
  • Review program health for the quarter and include experiment results
  • Find underperforming member segments and surface reactivation recommendations

How to install monitor-loyalty

Manually: put the files in place

.claude/commands/monitor-loyalty.md

Call it with /monitor-loyalty. For all projects use ~/.claude/commands/

Questions about monitor-loyalty

How do I install monitor-loyalty in Claude Code?

Save the command file to .claude/commands/monitor-loyalty.md in your project. Claude Code will load it automatically, and the command becomes available as /loyalty-lifecycle-orchestration:monitor-loyalty.

What does monitor-loyalty do?

It collects program data over your chosen period, diagnoses member health (engagement, churn risk, reward liability), highlights segments for action and win-back, and summarizes experiment outcomes. Output includes a KPI dashboard, risk and opportunity list, and a prioritized action backlog.

What parameters do I need to provide?

Required: time window (window: 7d, 30d, quarter) and report depth (detail: summary or full). Optional: breakdowns (dimensions: tier, cohort, region, channel), specific experiments to review, and KPI thresholds for escalation alerts.

Source text

monitor-loyalty.md · Apache-2.0
---
name: monitor-loyalty
description: Evaluates loyalty program performance, member health, and experiment impact.
usage: /loyalty-lifecycle-orchestration:monitor-loyalty --window 30d --detail full --dimensions "tier,region"
---

# Command: monitor-loyalty

## Inputs
- **window** – time range (7d, 30d, quarter) for analysis.
- **detail** – summary | full report depth.
- **dimensions** – optional breakdowns (tier, cohort, region, channel).
- **experiments** – optional list of campaigns/tests to review.
- **alert_threshold** – optional KPI threshold for escalations.

### GTM Agents Pattern & Plan Checklist
> Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325.

- **Pattern selection**: Monitoring typically runs **pipeline** (data → diagnostics → experiments → action plan). If diagnostics and experiment review can run in parallel, document a **diamond** segment with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing window, feeds, task IDs, dependency graph (BI, CRM, experimentation), error handling, and success metrics (retention, liability, engagement lift, alert remediation time).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for metric definition diffs, Context7 for SOPs/dashboards, Sequential Thinking for retro cadence, Playwright for verifying embedded dashboards.
- **Guardrails**: Default retry limit = 2 for failed data pulls or chart renders; escalation ladder = Member Insights Analyst → Loyalty Strategist → Exec sponsor.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before distributing outputs to ensure dependencies + approvals captured.

## Workflow
1. **Data Pull** – collect enrollment, engagement, redemption, CSAT, and revenue metrics by selected window.
2. **Health Diagnostics** – evaluate tier mix, churn risk, point liability, and reward breakage.
3. **Member Insights** – surface segments needing nudges, upgrade opportunities, or win-back plays.
4. **Experiment Review** – summarize test results with lift, guardrails, and recommendations.
5. **Action Plan** – produce prioritized backlog (journey tweaks, rewards refresh, messaging updates).

## Outputs
- Dashboard snapshot with KPI trends and drilldowns.
- Risk/Opportunity list referencing data points and owners.
- Experiment readouts plus next-test suggestions.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.

## Agent/Skill Invocations
- `member-insights-analyst` – owns analysis + insights.
- `loyalty-strategist` – validates roadmap adjustments.
- `member-insights` skill – ensures segmentation + reporting standards.

## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., Loyalty Strategist covering Analyst) when analysts unavailable.
- **Escalation triggers**: if alert_threshold is breached twice or liability spikes, trigger GTM Agents rip-cord escalation and record remediation in plan JSON.
- **Plan maintenance**: update plan JSON/change log when metrics, thresholds, or tooling stack shift to keep audit history accurate.

---

© gtmagents · Apache-2.0 · gtmagents/gtm-agents

Similar slash commands

All slash commands for AI and ML →

From the same set224

The whole set →
forecast-discipline forecast-discipline — a Claude Code skill that builds forecast-call methodology: commit/best case/pipeline tiers, inspection checklists, and accuracy thresholds. Runs when you prepare weekly or monthly sales forecasts. CX Codex +1 ★ 450repo stars plan-plays plan-plays builds an ABM playbook roadmap across account tiers, mapping plays, channels and timelines to a chosen campaign objective. CX Codex +1 ★ 450repo stars social-calendar-system social-calendar-system is a Claude Code skill that structures multi-channel social media calendars, approval routing, and publishing checklists. CX Codex +1 ★ 450repo stars distribute-assets distribute-assets is a Claude Code command that builds a channel-by-channel publishing and promotion plan with timing, UTMs, and partner coordination. It helps campaigns set clear owners and track results. CX Codex +1 ★ 450repo stars define-events define-events creates an analytics instrumentation specification with event schemas, owners, and QA steps. Useful when aligning tracking plans across CDPs, product analytics, and warehouses. CX Codex +1 ★ 450repo stars define-profiles The define-profiles command maps audience profile schemas, data sources, and activation needs. Use it to plan personalization across selected channels. CX Codex +1 ★ 450repo stars optimize-nurture optimize-nurture is a Claude Code command that turns nurture metrics and test results into an optimization plan. It flags weak stages and assigns follow-up work with owners and due dates. CX Codex +1 ★ 450repo stars co-plan-campaign co-plan-campaign builds a structured co-marketing campaign brief covering joint messaging, target audiences, asset ownership, and governance rules. CX Codex +1 ★ 450repo stars

Project sponsors

Companies that keep this analytics open