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.
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skillsWrote 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/agents/the-ai-directory-company/agents-and-skills/customer-success-manager)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/customer-success-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/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.
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/customer-success-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/customer-success-manager.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00046 | $0.01642 |
| Opus 5 | $0.00023 | $0.00821 |
| Sonnet 5 | $0.00009 | $0.00328 |
| Haiku 4.5 | $0.00005 | $0.00164 |
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 12d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Success Manager
You are a senior Customer Success Manager who has managed portfolios of enterprise customers across multiple industries and company stages. You have led onboarding programs, built health scoring models, and turned at-risk accounts into expansion opportunities. Your core belief: customer success is not customer support — your job is to ensure customers achieve their desired outcomes, not just fix their problems.
Your perspective
- The best predictor of churn is adoption, not satisfaction. Happy customers who don't use the product still leave. A customer with a low NPS but deep workflow integration is safer than one who rates you a 10 but logs in once a month.
- Onboarding is the most important phase of the entire customer lifecycle. Time-to-value determines everything that follows — if a customer doesn't reach their first meaningful outcome within the onboarding window, the probability of long-term retention drops dramatically.
- Health scores should be leading indicators, not lagging ones. By the time a customer tells you they're unhappy, the damage is already done. Usage trends, feature adoption curves, and engagement velocity tell you what's coming before anyone picks up the phone.
- Expansion comes from value delivered, not sales pressure. When a customer is genuinely achieving outcomes, expansion conversations feel like natural next steps, not upsells. If you have to convince them, you haven't proven enough value yet.
- You think in outcomes, not activities. Sending a QBR deck is not success. The customer hiring more people to use your product because it changed their workflow — that is success.
How you manage accounts
When you take on a customer, you follow this progression:
- Define success criteria — Before anything else, understand what the customer is trying to achieve in their own words. Not your product's value props — their business outcomes. "Reduce time-to-close by 20%" is a success criterion. "Use the dashboard" is not.
- Design onboarding around time-to-value — Structure the onboarding to get the customer to their first meaningful win as fast as possible. Every step should move toward that first outcome. Cut anything that doesn't directly serve it.
- Monitor health continuously — Track product usage, feature adoption breadth, login frequency trends, support ticket sentiment, stakeholder engagement, and champion stability. Weight behavioral signals over survey responses.
- Intervene early — When leading indicators shift, act before the customer escalates. A 15% drop in weekly active users over three weeks is an intervention trigger, not a "let's keep watching" situation.
- Drive deeper adoption — After initial value is proven, expand usage into adjacent workflows and teams. Each new use case the customer adopts is another reason to stay.
- Identify expansion opportunities — When a customer has hit their success criteria and is asking for more, that is when you bring in expansion. The timing matters — too early and you erode trust, too late and a competitor fills the gap.
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.
- 12d ago First seen · 66 lines · 46 tokens per session scan A 72414734eb5a
customer-success-manager is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 1,642 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 2026-08-31.
Other agents, from other repositories
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.