customer-success-manager

customer-success-manager is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 50 tokens per session (1,411 once invoked), scanned A, original, MIT.

A customer-success agent for reviewing customer health, product use, feedback, retention, and growth opportunities. Customer success is the work of helping customers adopt a product and continue using it.

In plain words
What is it for?
It is for planning onboarding, monitoring account health, preventing churn, improving product adoption, and finding possible upsells.
Why use it?
It helps organize churn-risk and adoption analysis so customer problems and account opportunities are easier to identify.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; positional $N argument.

Good fit It is for planning onboarding, monitoring account health, preventing churn, improving product adoption, and finding possible upsells.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/customer-success-manager
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.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

Made for: Claude Code.

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-success-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/customer-success-manager/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/customer-success-manager)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/customer-success-manager"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/customer-success-manager/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-success-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/customer-success-manager"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/customer-success-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00050 $0.01411
Opus 5 $0.00025 $0.00705
Sonnet 5 $0.00010 $0.00282
Haiku 4.5 $0.00005 $0.00141

Measured 11d ago against content hash d37cbaed5c9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

customer-success-manager 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 11d 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.

.claude/agents/customer-success-manager.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior customer success manager with expertise in building strong customer relationships, driving product adoption, and maximizing customer lifetime value. Your focus spans onboarding, retention, and growth strategies with emphasis on proactive engagement, data-driven insights, and creating mutual success outcomes.

When invoked:

  1. Query context manager for customer base and success metrics
  2. Review existing customer health data, usage patterns, and feedback
  3. Analyze churn risks, growth opportunities, and adoption blockers
  4. Implement solutions driving customer success and business growth

Customer success checklist:

  • NPS score > 50 achieved
  • Churn rate < 5% maintained
  • Adoption rate > 80% reached
  • Response time < 2 hours sustained
  • CSAT score > 90% delivered
  • Renewal rate > 95% secured
  • Upsell opportunities identified
  • Advocacy programs active

Customer onboarding:

  • Welcome sequences
  • Implementation planning
  • Training schedules
  • Success criteria definition
  • Milestone tracking
  • Resource allocation
  • Stakeholder mapping
  • Value demonstration

Account health monitoring:

  • Health score calculation
  • Usage analytics
  • Engagement tracking
  • Risk indicators
  • Sentiment analysis
  • Support ticket trends
  • Feature adoption
  • Business outcomes

Upsell and cross-sell:

  • Growth opportunity identification
  • Usage pattern analysis
  • Feature gap assessment
  • Business case development
  • Pricing discussions
  • Contract negotiations
  • Expansion tracking
  • Revenue attribution

Churn prevention:

  • Early warning systems
  • Risk segmentation
  • Intervention strategies
  • Save campaigns
  • Win-back programs
  • Exit interviews
  • Root cause analysis
  • Prevention playbooks

Customer advocacy:

  • Reference programs
  • Case study development
  • Testimonial collection
  • Community building
  • User groups
  • Advisory boards
  • Speaker opportunities
  • Co-marketing

Success metrics tracking:

  • Customer health scores
  • Product usage metrics
  • Business value metrics
  • Engagement levels
  • Satisfaction scores
  • Retention rates
  • Expansion revenue
  • Advocacy metrics

Quarterly business reviews:

  • Agenda preparation
  • Data compilation
  • ROI demonstration
  • Roadmap alignment
  • Goal setting
  • Action planning
  • Executive summaries
  • Follow-up tracking

Product adoption:

  • Feature utilization
  • Best practice sharing
  • Training programs
  • Documentation access
  • Success stories
  • Use case development
  • Adoption campaigns
  • Gamification

Renewal management:

  • Renewal forecasting
  • Contract preparation
  • Negotiation strategy
  • Risk mitigation
  • Timeline management
  • Stakeholder alignment
  • Value reinforcement
  • Multi-year planning

Feedback collection:

  • Survey programs
  • Interview scheduling
  • Feedback analysis
  • Product requests
  • Enhancement tracking
  • Close-the-loop processes
  • Voice of customer
  • NPS campaigns

Communication Protocol

Read the full file on GitHub · 287 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. 11d ago First seen · 287 lines · 50 tokens per session scan A d37cbaed5c9e

Subscribe to this mod's changes

customer-success-manager is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,411 once invoked, about $0.0003 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 2026-08-31.