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 multiplex-ai/muggle-ai-teams --skill churn-preventiongit clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teamsWrote 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/multiplex-ai/muggle-ai-teams/churn-prevention)<a href="https://agentmods.dev/skills/multiplex-ai/muggle-ai-teams/churn-prevention"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-teams/churn-prevention/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/multiplex-ai/muggle-ai-teams/churn-prevention"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-teams/churn-prevention.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 | $0.00156 | $0.04208 |
| Opus 5.5 | $0.00062 | $0.01683 |
| Sonnet 5.5 | $0.00031 | $0.00842 |
| Haiku 4.5 | $0.00016 | $0.00421 |
Grade A, and why
churn-prevention 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 5d 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.
This is a copy
95% identical to churn-prevention — 38 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Churn Prevention
You are an expert in SaaS retention and churn prevention. Your goal is to help reduce both voluntary churn (customers choosing to cancel) and involuntary churn (failed payments) through well-designed cancel flows, dynamic save offers, proactive retention, and dunning strategies.
Before Starting
Check for product marketing context first:
If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Gather this context (ask if not provided):
1. Current Churn Situation
- What's your monthly churn rate? (Voluntary vs. involuntary if known)
- How many active subscribers?
- What's the average MRR per customer?
- Do you have a cancel flow today, or does cancel happen instantly?
2. Billing & Platform
- What billing provider? (Stripe, Chargebee, Paddle, Recurly, Braintree)
- Monthly, annual, or both billing intervals?
- Do you support plan pausing or downgrades?
- Any existing retention tooling? (Churnkey, ProsperStack, Raaft)
3. Product & Usage Data
- Do you track feature usage per user?
- Can you identify engagement drop-offs?
- Do you have cancellation reason data from past churns?
- What's your activation metric? (What do retained users do that churned users don't?)
4. Constraints
- B2B or B2C? (Affects flow design)
- Self-serve cancellation required? (Some regulations mandate easy cancel)
- Brand tone for offboarding? (Empathetic, direct, playful)
How This Skill Works
Churn has two types requiring different strategies:
| Type | Cause | Solution |
|---|---|---|
| Voluntary | Customer chooses to cancel | Cancel flows, save offers, exit surveys |
| Involuntary | Payment fails | Dunning emails, smart retries, card updaters |
Voluntary churn is typically 50-70% of total churn. Involuntary churn is 30-50% but is often easier to fix.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 425 lines · 156 tokens per session scan A 8cb4d4992cd1
churn-prevention is a skill published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed 2d ago), licensed MIT. It adds 156 tokens to every session and 4,208 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to churn-prevention, differing in 38 lines, and is treated as a copy.
Other skills, from other repositories
codex-handoff
Three-phase delivery workflow — Claude plans and writes a spec, a Claude subagent implements in the host working tree, a fresh Codex session adversarially reviews the diff (via the codex-plugin-cc plugin). Implementation and review are never the same model. Use for any change touching more than one file or real…
discuss
Decision-lock workflow for complex features. Asks targeted domain-specific questions, locks scope, and writes a CONTEXT.md that downstream skills consume. Auto-invoked when a feature touches 3+ files across 2+ concerns, or manually via /discuss.
skill-name
One-line description of what this skill does and when it triggers.
codex-handoff
Three-phase delivery workflow — Claude plans and writes a spec, a Claude subagent implements in the host working tree, a fresh Codex session adversarially reviews the diff (via the codex-plugin-cc plugin). Implementation and review are never the same model. Use for any change touching more than one file or real…
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.