Skip to main content
command CX Codex

monitor-personalization — Claude Code command: setup and use

monitor-personalization audits personalization campaigns, tracks experiment outcomes, and flags consent violations across user segments.

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-personalization.md
Open on GitHub

What monitor-personalization does

The command runs an end-to-end review of personalization initiatives. It pulls engagement and revenue metrics, inspects consent flags and fallback rates, and summarizes running experiments with statistical confidence scores. Audit records land directly in .claude/plans/plan-<timestamp>.json.

Execution follows a five-step pipeline covering data aggregation, governance scanning, experiment readouts, anomaly detection, and report generation. The workflow calls the testing-lead and personalization-architect roles alongside the governance skill.

Failed data collection jobs stop after two retries before escalating up the lead chain.

What it helps with

  • Track statistical confidence across active personalization experiments
  • Audit consent flags, rule change logs, and fallback triggers
  • Detect metric drops and variant suppression anomalies
  • Generate audit plan snapshots in .claude/plans

Example prompts for the agent

  • /personalization-engine:monitor-personalization --initiative "PLG Onboarding" --window 14d --detail full
  • /personalization-engine:monitor-personalization --initiative "Enterprise Checkout" --window 30d --alert_threshold 0.05
  • /personalization-engine:monitor-personalization --initiative "Mobile Activation" --window 7d --dimension channel

How to install monitor-personalization

Manually: put the files in place

.claude/commands/monitor-personalization.md

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

Questions about monitor-personalization

How to install monitor-personalization in Claude Code?

Place the command definition file at .claude/commands/monitor-personalization.md in your project root. Claude Code registers the command immediately.

What does monitor-personalization do?

It audits campaign performance, verifies consent governance, and inspects A/B test confidence. Findings and next steps are logged into an audit plan JSON file.

How does error handling work during metric collection?

The command allows up to 2 retries on failed data pulls. If alerts repeat or thresholds are breached twice, it routes the incident to testing and privacy leads.

Source text

monitor-personalization.md · Apache-2.0
---
name: monitor-personalization
description: Audits personalization performance, governance compliance, and experiment results.
usage: /personalization-engine:monitor-personalization --initiative "PLG Onboarding" --window 14d --detail full
---

# Command: monitor-personalization

## Inputs
- **initiative** – personalization program or campaign to analyze.
- **window** – time frame (7d, 14d, 30d) for pulling metrics.
- **detail** – summary | full to control report depth.
- **dimension** – optional breakdown (profile, channel, cohort).
- **alert_threshold** – optional KPI threshold to trigger incident items.

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

- **Pattern selection**: Monitoring usually runs **pipeline** (data aggregation → governance scan → experiment readout → issue detection → action plan). If governance + experiments review can run concurrently, capture a **diamond** block with merge gate in the plan header.
- **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing initiative, data feeds, dependency graph (data eng, privacy, experimentation), error handling, and success metrics (lift %, incident response time, consent adherence).
- **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for schema diffs, Context7 for governance/experiment SOPs, Sequential Thinking for retro cadence, Playwright for experience QA evidence.
- **Guardrails**: Default retry limit = 2 for failed data pulls or anomaly jobs; escalation ladder = Testing Lead → Personalization Architect → Data Privacy Lead.
- **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before distribution to ensure dependencies + approvals are logged.

## Workflow
1. **Data Aggregation** – pull engagement, conversion, and revenue impact by profile/channel plus decision tree health signals.
2. **Governance Scan** – verify consent flags, fallback rates, and rule change logs for compliance.
3. **Experiment Readout** – summarize live/completed tests with statistical confidence and recommended actions.
4. **Issue Detection** – flag anomalies (data freshness, variant suppression, performance dips) and suggest playbooks.
5. **Report Distribution** – publish recap with dashboards, backlog items, and owners.

## Outputs
- Performance dashboard snapshot segmented by profile/channel/variant.
- Governance checklist status with any violations or pending approvals.
- Experiment memo with next steps + rollout guidance.
- Plan JSON entry stored/updated in `.claude/plans` for audit trail.

## Agent/Skill Invocations
- `testing-lead` – interprets experiments and recommends rollouts.
- `personalization-architect` – validates experience integrity.
- `governance` skill – enforces policy checks and approvals.

## GTM Agents Safeguards
- **Fallback agents**: document substitutes (e.g., Governance covering Testing Lead) when leads unavailable.
- **Escalation triggers**: escalate if alert_threshold breached twice, consent violations appear, or anomaly alerts repeat; log remediation steps in plan JSON.
- **Plan maintenance**: update plan JSON/change log when metrics, thresholds, or monitoring cadences change to keep audits accurate.

---

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

Similar slash commands

All slash commands for Marketing and content →

From the same set224

The whole set →
manage-assets manage-assets — a command for orchestrating co-branded asset production, approvals, and distribution across partner teams. Tracks asset inventory, routes review workflows, and packages deliverables for activation. CX Codex +1 ★ 450repo stars optimize-referrals optimize-referrals analyzes referral conversion funnels, fraud patterns, and partner health to generate structured optimization plans in Claude Code. CX Codex +1 ★ 450repo stars synthesize-feedback The synthesize-feedback command turns customer signals into ranked themes and estimates their impact. Use it to prepare evidence and follow-up priorities from feedback. CX Codex +1 ★ 450repo stars define-handoff define-handoff — a command to design lead-to-sales handoff: sets routing rules, response SLAs, and enablement requirements for each sales pod or segment. CX Codex +1 ★ 450repo stars editorial-ops editorial-ops is a Claude Code skill that plans multi-channel editorial calendars and coordinates GTM content production from ideation through distribution, with KPI guardrails set before assets ship. CX Codex +1 ★ 450repo stars measure-engagement measure-engagement pulls community health metrics, sentiment, and experiment results into one report with a prioritized action list. Use it when you need to see what is happening in a community and what to do about it. CX Codex +1 ★ 450repo stars prioritize-gaps prioritize-gaps scores customer journey friction points, assigns owners, and creates remediation roadmaps. Helps teams prioritize fixes across onboarding and lifecycle stages. CX Codex +1 ★ 450repo stars map-journey map-journey — a Claude Code command that runs a structured journey mapping workshop, from research compilation to a gap log with assigned owners. Takes persona, scope, and time horizon as inputs. CX Codex +1 ★ 450repo stars

Project sponsors

Companies that keep this analytics open