segment-wizard

segment-wizard is a skill for Claude Code from reatlat/fullstory-claude-plugin. It costs 48 tokens per session (1,182 once invoked), scanned A, original, MIT.

A guided tool for building user segments, which are groups of users that match chosen conditions. It asks step-by-step questions and checks the result for non-technical users.

In plain words
What is it for?
It helps create groups such as users who visited a pricing page but did not sign up, or active enterprise users who are not on a trial.
Why use it?
It removes the need to know query syntax or translate a detailed audience description into technical rules yourself.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fullstory-claude-plugin plugin — 46 skills, 3 agents, 1 MCP server shipped together

Good fit It helps create groups such as users who visited a pricing page but did not sign up, or active enterprise users who are not on a trial.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reatlat/fullstory-claude-plugin/segment-wizard
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 reatlat/fullstory-claude-plugin --skill segment-wizard
Clone the repo
git clone --depth 1 https://github.com/reatlat/fullstory-claude-plugin

Made for: Claude Code.

Or install fullstory-claude-plugin, the plugin that ships this one along with the rest of its 46 skills, 3 agents, 1 MCP server.

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 segment-wizard

README.md
[![agentmods](https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/segment-wizard/github.svg)](https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/segment-wizard)
Your own site
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/segment-wizard"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/segment-wizard/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.

agentmods 80×15 button for segment-wizard

Your own site · 80×15
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/segment-wizard"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/segment-wizard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,182 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01182
Opus 5 $0.00024 $0.00591
Sonnet 5 $0.00010 $0.00236
Haiku 4.5 $0.00005 $0.00118

Measured 9d ago against content hash 77c758a6c379, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

segment-wizard 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 9d 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/segment-wizard/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Segment Wizard

Guided, step-by-step segment building for non-technical users. Helps PMs, designers, and support build precise user cohorts without knowing the query syntax.

When to Use

  • "I need a segment of users who did X but not Y"
  • "Build a segment for our target audience — I'll describe who they are"
  • "I want to find users who visited the pricing page but didn't sign up"
  • "Create a cohort of power users for me — active, enterprise, non-trial"
  • "Help me build a segment — I'm not sure how to express this"

The segment-wizard is invoked when the user struggles to express a segment as a natural-language query, or when general-analysis detects that a build_segment call returned a segment that doesn't match what the user described.

Workflow

Step 1: Interview the user

Ask structured questions to narrow down the cohort:

Time window:

  • "New users this month, or all users regardless of when they joined?"
  • "Users active in the last 7 days, or any user who's ever been active?"

Behavioral criteria:

  • "What did they do? (visit a page, click something, complete an action, see an error)"
  • "What did they NOT do? (didn't convert, didn't return, didn't complete onboarding)"

User properties (if they have custom properties):

  • "What plan are they on? What role? What country?"

Engagement level:

  • "Power users (many sessions) or casual users (few sessions)?"
  • "Have they been active recently?"

Step 2: Translate to query

Turn the user's answers into a build_segment query:

User says:

  • "People who visited the pricing page in the last 30 days"
  • "But didn't sign up"
  • "On enterprise plan"
  • "Active in the last 7 days"

Query: "enterprise plan users who visited /pricing in last 30 days, did not visit /signup/confirmation, and were active in last 7 days"

Step 3: Validate the segment

Build the segment, then verify it matches expectations:

fullstory:build_segment(query) → segment_id
fullstory:get_sessions(segment_id, limit=5)

Read the full file on GitHub · 109 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. 9d ago First seen · 109 lines · 48 tokens per session scan A 77c758a6c379

Subscribe to this mod's changes

segment-wizard is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 27d ago), licensed MIT. It adds 48 tokens to every session and 1,182 once invoked, about $0.0002 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 2026-08-30.