Audience Segmenter

Audience Segmenter is a skill for Claude Code, Codex from eddiebelaval/squire. It costs 12 tokens per session (973 once invoked), scanned A, original, MIT.

A guide for dividing customers or other audiences into groups based on traits such as behaviour, demographics, interests, value, or lifecycle stage.

In plain words
What is it for?
Use it to define audience segments and plan targeted marketing, personalised messages, and channel strategies.
Why use it?
It helps avoid sending the same message to everyone when different groups need different offers or communication.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/eddiebelaval/squire/audience-segmenter
Any agent
npx skills add eddiebelaval/squire --skill audience-segmenter
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

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.

agentmods badge for Audience Segmenter

README.md
[![agentmods](https://agentmods.dev/badge/skills/eddiebelaval/squire/audience-segmenter.svg)](https://agentmods.dev/skills/eddiebelaval/squire/audience-segmenter)
Your own site
<a href="https://agentmods.dev/skills/eddiebelaval/squire/audience-segmenter"><img src="https://agentmods.dev/badge/skills/eddiebelaval/squire/audience-segmenter.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 973 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00973
Opus 5 $0.00006 $0.00487
Sonnet 5 $0.00002 $0.00195
Haiku 4.5 $0.00001 $0.00097

Measured yesterday against content hash cf02d143c7d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Audience Segmenter 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 yesterday.

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/audience-segmenter/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audience Segmenter

Divide your audience into meaningful segments that enable targeted, personalized marketing at scale. This skill helps you identify distinct customer groups based on behavior, demographics, psychographics, and value, then tailor your messaging and offers accordingly.

One-size-fits-all marketing underperforms. This skill provides frameworks for discovering natural audience clusters, defining segment criteria, and developing differentiated strategies for each group. The result: higher relevance, better engagement, and improved conversion across all marketing channels.

Essential for marketers, product managers, and growth teams who want to move beyond generic messaging to true personalization.

Core Workflows

Workflow 1: Behavioral Segmentation

  1. Usage Pattern Analysis - How customers interact with product
  2. Purchase Behavior - Frequency, recency, monetary value (RFM)
  3. Engagement Levels - Email opens, site visits, feature usage
  4. Lifecycle Stage - New, active, at-risk, churned
  5. Feature Adoption - Which capabilities they use
  6. Channel Preference - Where they engage most
  7. Segment Definition - Actionable behavioral groups

Workflow 2: Persona Development

  1. Research Foundation - Interviews, surveys, data analysis
  2. Demographic Profiles - Role, company size, industry
  3. Psychographic Insights - Goals, challenges, motivations
  4. Decision-Making Process - How they evaluate and buy
  5. Information Sources - Where they learn and research
  6. Objection Mapping - Common hesitations and concerns
  7. Persona Documentation - Shareable persona cards

Workflow 3: Value-Based Segmentation

  1. Customer Lifetime Value Calculation - LTV by customer
  2. Profitability Analysis - Revenue minus cost to serve
  3. Growth Potential - Expansion opportunity scoring
  4. Churn Risk Assessment - Likelihood of leaving
  5. Tier Definition - VIP, standard, low-value segments
  6. Resource Allocation - Investment by segment value
  7. Retention Strategy - Differentiated approaches

Read the full file on GitHub · 99 lines

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.

  1. yesterday First seen · 99 lines · 12 tokens per session scan A cf02d143c7d2

Subscribe to this mod's changes

Audience Segmenter is a skill published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 19d ago), licensed MIT. It adds 12 tokens to every session and 973 once invoked, about $0.0001 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 2026-09-03.