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 skills add alexclowe/awesome-claude-cowork-plugins --skill client-retentiongit clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/skills/alexclowe/awesome-claude-cowork-plugins/client-retention)<a href="https://agentmods.dev/skills/alexclowe/awesome-claude-cowork-plugins/client-retention"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-claude-cowork-plugins/client-retention/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/skills/alexclowe/awesome-claude-cowork-plugins/client-retention"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-claude-cowork-plugins/client-retention.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 | $0.00016 | $0.00774 |
| Opus 5.5 | $0.00006 | $0.00310 |
| Sonnet 5.5 | $0.00003 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
client-retention 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 23d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- client-retention — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You understand how to build and maintain insurance client relationships effectively. When the user is preparing client communications, retention strategies, or cross-selling approaches, apply these principles automatically.
Core competencies
Annual review best practices:
- Trigger reviews proactively — don't wait for the client to call
- Review life changes: marriage, divorce, new home, new baby, teen driver, retirement, business changes
- Coverage adequacy check: are limits keeping pace with inflation and asset growth?
- Discount audit: are all eligible discounts being applied (bundling, claims-free, loyalty, safety features, professional affiliations)?
- Beneficiary review: especially after major life events
- Structure reviews as 15–20 minute conversations with a clear agenda
- Follow up with a written summary of recommendations
Cross-selling that adds value:
- Identify genuine coverage gaps, not just premium opportunities
- Connect recommendations to the client's specific life situation
- Use "risk conversation" framing: "If X happened, here's what would/wouldn't be covered"
- Bundle strategically — show the net savings, not just the additional premium
- Common natural cross-sells:
- Home + auto → umbrella
- Auto → life (especially young families)
- Home → flood (if in or near a flood zone)
- Business → commercial auto, cyber liability, key person
- Individual health → disability income, critical illness
Retention strategies when clients shop around:
- Don't panic or get defensive — it's normal and healthy
- Offer to review the competitor's quote objectively — compare apples to apples (same coverage limits, deductibles, endorsements)
- Highlight value beyond price: claims handling, local presence, advisory relationship, carrier financial strength
- If rate is genuinely non-competitive, explore options: adjust deductibles, remove unnecessary coverage, check for missed discounts, remarket with other carriers
- "Match and beat" isn't always the answer — sometimes the honest conversation is "Here's why paying a bit more with us may be worth it"
- If the client does leave, handle it gracefully — they may come back
Claims handling communication:
- Be the client's advocate and guide through the process
- Set clear expectations about timeline and process
- Provide proactive updates — don't make the client chase you
- After resolution, check in on satisfaction
- Use claims experience as a relationship-strengthening moment, not just an administrative process
- Discuss coverage adjustments post-claim when appropriate (not immediately — let the dust settle)
Building referral relationships:
- Earn referrals through exceptional service, don't just ask for them
- Create referral-worthy moments: claims handled smoothly, coverage that saved the day, proactive outreach that caught a gap
- Make it easy to refer: provide shareable content, referral cards, or a simple link
- Thank referrers promptly and genuinely
- Partner with complementary professionals: real estate agents, mortgage brokers, accountants, attorneys, auto dealers
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.
- 23d ago First seen · 67 lines · 16 tokens per session scan A bfa00ddfffbd
client-retention is a skill published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 774 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
sox-itgc
Expert SOX IT General Controls (ITGC) advisor for finance, internal audit and IT compliance teams. Covers the four ITGC domains external auditors test for SOX 404 — access to programs and data, program changes, computer operations, and program development — plus scoping in-scope systems from the financial statements…
monetization-strategy
Revenue models, pricing strategies, and business monetization. Use when designing pricing, choosing business models, or optimizing revenue for products and services.
agent-payment-billing-specialist
Specialist subagent: Stripe integration, subscription billing, webhooks, PCI compliance, and tax handling specialist. Use when implementing payments, subscriptions, metered billing, or checkout flows. Trigger phrases: payment, billing, Stripe, subscription, checkout, invoice, webhook, PCI, pricing, plan.
financial-scenario-planner
Stress-test financial plans across scenarios (bull/bear/base), sensitivity tables, and Monte Carlo-style analysis. Use when evaluating financial assumptions, modeling risk scenarios, or building scenario-based financial plans.
financial-analysis
Build financial models, perform valuations, analyze cost structures, and develop business cases. Use this skill when the user mentions: financial analysis, financial model, DCF, valuation, P&L, revenue model, cost structure, unit economics, break-even, ROI, NPV, IRR, sensitivity analysis, pro forma, three-statement…
nl-tax-box1-home
Use when an owning Dutch tax workflow needs sourced Box 1 or own-home facts and questions; use annual 2025 evidence for annual workpacks and labeled 2026 estimates for provisional workpacks.