persona-builder

persona-builder is a skill for Claude Code from reatlat/fullstory-claude-plugin. It costs 52 tokens per session (1,376 once invoked), scanned A, original, MIT.

A user-grouping guide that builds personas from how people actually use a product, rather than from assumed demographics.

In plain words
What is it for?
Use it to compare frequent and occasional users, understand users who convert or do not, and define groups such as power users.
Why use it?
It replaces guesswork about users with behavior-based groups that are useful for product decisions.

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 Use it to compare frequent and occasional users, understand users who convert or do not, and define groups such as power users.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reatlat/fullstory-claude-plugin/persona-builder
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 persona-builder
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 persona-builder

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/persona-builder"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/persona-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,376 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 $0.00052 $0.01376
Opus 5 $0.00026 $0.00688
Sonnet 5 $0.00010 $0.00275
Haiku 4.5 $0.00005 $0.00138

Measured 11d ago against content hash 03a11fa170b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

persona-builder 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.

skills/persona-builder/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona Builder

Build behavioral personas from real session data — identify who your users actually are based on what they do, not what you assume.

When to Use

  • "What types of users do we have?"
  • "Build personas for the product team"
  • "Who are our power users vs casual users?"
  • "What's the difference between users who convert and users who don't?"
  • "Define our ideal customer profile from behavioral data"

Mental Model

Traditional personas are built from interviews and assumptions. Behavioral personas are built from what users actually do. The difference matters:

  • "Sarah the Marketing Manager, 34, Chicago" — traditional persona (demographic)
  • "The Power Browser: visits 3+ times/week, compares products extensively, reads reviews, converts on 4th visit" — behavioral persona (what matters for product decisions)

Workflow

Step 1: Discover behavioral clusters

Run broad metrics to find natural grouping dimensions:

fullstory:build_metric(query="sessions per user in last 30 days", output_type="top_n")
fullstory:build_metric(query="pages per session", output_type="top_n")
fullstory:build_metric(query="time on site per session", output_type="top_n")
fullstory:build_metric(query="features used per user", output_type="top_n")

Look for natural breakpoints:

  • Session count: 1 (one-and-done), 2-5 (occasional), 6-20 (regular), 20+ (power)
  • Pages per session: 1-2 (bouncers), 3-5 (browsers), 6+ (deep explorers)
  • Features: 1-2 (single-purpose), 3-5 (multi-feature), 6+ (power user)

Step 2: Build segments for each cluster

fullstory:build_segment("users with 20+ sessions in last 30 days") → power_users
fullstory:build_segment("users with 1 session in last 30 days") → one_timers
fullstory:build_segment("users with 2-5 sessions, 3-5 pages per session") → casual_browsers

Step 3: Profile each persona

For each segment, pull sessions and analyze:

fullstory:get_sessions(segment_id, limit=10)
→ session-context: "What is this user's typical flow? What features do they use? What frustrates them? What do they achieve?"

Read the full file on GitHub · 130 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. 11d ago First seen · 130 lines · 52 tokens per session scan A 03a11fa170b0

Subscribe to this mod's changes

persona-builder is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 29d ago), licensed MIT. It adds 52 tokens to every session and 1,376 once invoked, about $0.0003 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.