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 Maudeunfledged834/startup-founder-skills --skill churn-analysisgit clone --depth 1 https://github.com/Maudeunfledged834/startup-founder-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/skills/maudeunfledged834/startup-founder-skills/churn-analysis)<a href="https://agentmods.dev/skills/maudeunfledged834/startup-founder-skills/churn-analysis"><img src="https://agentmods.dev/badge/skills/maudeunfledged834/startup-founder-skills/churn-analysis/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/maudeunfledged834/startup-founder-skills/churn-analysis"><img src="https://agentmods.dev/badge/skills/maudeunfledged834/startup-founder-skills/churn-analysis.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 | $0.00038 | $0.02044 |
| Opus 5 | $0.00019 | $0.01022 |
| Sonnet 5 | $0.00008 | $0.00409 |
| Haiku 4.5 | $0.00004 | $0.00204 |
Grade A, and why
churn-analysis 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.
This is a copy
100% identical to churn-analysis — 0 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Churn Analysis
When to Use
Activate when a founder needs to identify at-risk accounts before they churn, diagnose churn drivers, build a customer health scoring system, design cancellation or save flows, recover failed payments, or re-engage lost customers. This includes prompts like "our churn is too high," "which customers are about to leave," "why are customers canceling," "build a customer health score," "set up dunning emails," or "create a win-back campaign." Especially relevant for seed/Series A teams managing customers manually without dedicated CS platforms like Gainsight or ChurnZero.
Context Required
- From startup-context: business model (B2B/B2C, subscription/usage-based), current churn rate (logo and revenue), customer segments, pricing tiers, contract terms, product usage data availability, and current retention tooling.
- From the user: available data sources (support tickets, Slack channels, NPS scores, usage logs, email logs, billing data), what "healthy" customer behavior looks like, any historical churn patterns, whether churn is primarily voluntary or involuntary, and the specific churn problem to solve.
Work with whatever data is available. Early-stage companies often lack formal CS systems — the skill works with support inboxes, Slack history, and spreadsheets.
Workflow
- Intake and baseline — Gather all available customer data: customer lists, support tickets, Slack/communication history, NPS scores, usage data, email logs, and billing records. Establish what "healthy" looks like and identify any known churn patterns.
- Extract signals — Analyze four signal categories across every account: support signals, communication signals, usage signals, and commercial signals (see framework below).
- Score risk — Build a composite risk score (0-100) for each account using weighted signal categories. Higher score means higher risk.
- Generate save plays — For high-risk accounts, produce specific interventions: root cause hypothesis, recommended actions, talk tracks for the CS conversation, and escalation triggers.
- Build the weekly scorecard — Compile into a weekly risk report with account-by-account analysis, MRR at risk, trend data, signal distribution, and recommended focus areas.
- Design interventions — For each churn driver identified, design the appropriate intervention: product fix, CS outreach, cancel flow save offer, dunning sequence, or win-back campaign.
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.
- 11d ago First seen · 123 lines · 38 tokens per session scan A af5a0801dee2
churn-analysis is a skill published in the GitHub repository Maudeunfledged834/startup-founder-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 2,044 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to churn-analysis, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
deploy-site
Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.