What is customer-health-modeling?

A process for defining and evaluating a customer or account health model. Such a model combines chosen signals into a view of current value or a forecast of a specific future outcome, such as renewal risk.

Use it to specify health scores, renewal or churn-risk models, decision thresholds, reason codes, validation checks, monitoring, and governance.

It prevents one universal score or raw usage number from being treated as the complete truth about a customer.

customer-health-modeling — Skill by krillinai/growth-skills

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.

Any agent

npx skills add krillinai/growth-skills --skill customer-health-modeling

Clone the repo

git clone --depth 1 https://github.com/krillinai/growth-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/krillinai/growth-skills/customer-health-modeling/github.svg)](https://agentmods.dev/skills/krillinai/growth-skills/customer-health-modeling)

Your own site

<a href="https://agentmods.dev/skills/krillinai/growth-skills/customer-health-modeling"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/customer-health-modeling/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/krillinai/growth-skills/customer-health-modeling"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/customer-health-modeling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,077 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00098	$0.03077
Opus 5.5	$0.00039	$0.01231
Sonnet 5.5	$0.00020	$0.00615
Haiku 4.5	$0.00010	$0.00308

Measured 2mo ago against content hash f2d8721a64ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

customer-health-modeling 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 2mo 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.

skills/retention/references/modules/customer-health-modeling/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Customer Health Modeling

Build a versioned, decision-specific view of current customer value or a calibrated prediction of a defined future customer outcome. Health is not customer truth, one universal score, usage volume, renewal status, sentiment, or expansion propensity alone. Separate observed state, prediction, causal mechanism, treatment response, recommendation, action, and outcome.

Read customer-health-contract-and-labels.md before accepting the customer entity, hierarchy, decision, outcome, prediction time, horizon, label, cohort, maturity, or evidence. Read features-models-and-validation.md before using product, support, relationship, commercial, or human signals; designing features; selecting a rule, scorecard, survival, or predictive model; or validating leakage, discrimination, calibration, and thresholds. Read decisions-monitoring-and-governance.md before creating action bands, reason codes, suppressions, overrides, monitoring, market transfer, privacy, or external handoffs. Read output-contract.md before delivery. Use playbook-sources.md for the pinned Growth Playbook basis.

Select One Mode

Mode	Use
`specification`	Define a calculation-ready customer, outcome, feature, label, validation, and decision contract when compatible evidence is unavailable
`build`	Build a bounded rule, dimensional view, scorecard, survival model, or prediction specification from supplied compatible evidence
`audit`	Inspect an existing model, score, dashboard, band, route, or claimed outcome for validity, leakage, calibration, safety, and governance
`validate`	Evaluate a supplied model or ruleset on mature out-of-time outcomes and the intended decision population
`monitor`	Review population, features, labels, calibration, performance, actions, and outcomes for drift or feedback
`refresh`	Preserve the prior version and update affected data, labels, features, model, thresholds, actions, or governance after material change

Read the full file on GitHub · 110 lines

Files

What ships with it

5 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.

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.

2mo ago First seen · 110 lines · 98 tokens per session scan A f2d8721a64ef

Subscribe to this mod's changes

customer-health-modeling is a skill published in the GitHub repository krillinai/growth-skills (43 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 3,077 once invoked, about $0.0004 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 2026-09-03.

Analytics and metrics

customer-health-modeling next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
customer-health-modelingkrillinai/growth-skills	Skill	43	2mo ago	MIT	A	98	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code