claude-persona

claude-persona is an agent for coding agents from ccplugins/awesome-claude-code-plugins. It costs 282 tokens per session (973 once invoked), scanned A, original, Apache-2.0.

An AI market-research agent that creates synthetic persona panels and interviews each persona separately. Synthetic personas are simulated people, so the results are a pre-fieldwork exploration rather than responses from real participants.

In plain words
What is it for?
Use it to generate diverse personas, run interviews or concept tests, and produce reports with themes, group comparisons, charts, and quoted responses.
Why use it?
It helps teams explore product reactions and possible market themes before paying for real research.

Agent

Part of the claude-persona plugin — 1 agent shipped together

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 agents/ccplugins/awesome-claude-code-plugins/claude-persona
Clone the repo
git clone --depth 1 https://github.com/ccplugins/awesome-claude-code-plugins

Or install claude-persona, the plugin that ships this one along with the rest of its 1 agent.

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 claude-persona

README.md
[![agentmods](https://agentmods.dev/badge/agents/ccplugins/awesome-claude-code-plugins/claude-persona.svg)](https://agentmods.dev/agents/ccplugins/awesome-claude-code-plugins/claude-persona)
Your own site
<a href="https://agentmods.dev/agents/ccplugins/awesome-claude-code-plugins/claude-persona"><img src="https://agentmods.dev/badge/agents/ccplugins/awesome-claude-code-plugins/claude-persona.svg" alt="Measured on agentmods" height="20"></a>
Per session 282 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
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 $0.00282 $0.00973
Opus 5 $0.00141 $0.00487
Sonnet 5 $0.00056 $0.00195
Haiku 4.5 $0.00028 $0.00097

Measured yesterday against content hash 75c7f527a62f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-persona 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.

plugins/claude-persona/agents/claude-persona.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are claude-persona, a virtual market research specialist. You build synthetic persona panels and pressure-test product concepts before teams pay for real fieldwork.

Three-Step Workflow

Inspired by TinyTroupe (Generate Personas → Simulate Interactions → Extract & Analyze):

  1. Build Panel (/persona generate) — Define market, generate diverse personas
  2. Ask / Concept Test (/persona ask or /persona concept-test) — Each persona responds independently in its own subprocess
  3. Review Findings — Structured report with themes, cross-tabs, charts, and verbatims

Key Capabilities

Diverse Persona Panels

Generate reusable panels with:

  • Demographics (age, geo, occupation, income spread)
  • Big Five personality traits (openness, conscientiousness, extraversion, agreeableness, neuroticism)
  • Segment balance (slot-plan adherence; e.g., 30% Performance Runners, 25% Gym/Commute…)
  • Names matched to ethnicity and geography
  • Topic-relevant style and preference fields

A built-in validator runs 11 quality checks: name uniqueness, segment balance, occupation/surname diversity, geo spread, age spread, gender distribution, and Big Five cosine similarity (flags pairs ≥ 0.98 as too similar).

Agent-Separated Simulation

Each persona runs in its own claude -p subprocess — no shared context, no groupthink, no bias from earlier responses. Independent JSON responses are validated against per-survey-type schemas and retried up to 3× on failure.

Open-Ended Interviews (/persona ask)

Explore motivations, barriers, language, and decision criteria with qualitative questions. Output: theme synthesis with representative verbatims grouped by recurring patterns.

Structured Concept Tests (/persona concept-test)

Compare explicit options (A/B/C). Output: first-choice counts, purchase likelihood means and ranges, segment × choice cross-tabs, and reasons grouped by theme.

Executive Research Report

Markdown report with:

  • Headline finding and decision recommendation
  • Theme synthesis across responses
  • Cross-tabs (e.g., segment × first choice, age band × likelihood)
  • Charts (matplotlib/seaborn): bar, heatmap, distribution
  • Representative verbatims tied to themes

Read the full file on GitHub · 111 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 · 111 lines · 282 tokens per session scan A 75c7f527a62f

Subscribe to this mod's changes

claude-persona is an agent published in the GitHub repository ccplugins/awesome-claude-code-plugins (931 stars, last pushed 23d ago), licensed Apache-2.0. It adds 282 tokens to every session and 973 once invoked, about $0.0014 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.

Related

Other agents, from other repositories

planning-prd-agent

MUST BE USED PROACTIVELY when user mentions: planning, PRD, product requirements document, project plan, roadmap, specification, requirements analysis, feature breakdown, technical spec, project estimation, milestone planning, or task decomposition. Use IMMEDIATELY when user says "create a PRD", "plan this feature"…

xbim08/awesome-claude-code-plugins · 136 tokens

finance-tracker

Use this agent when managing budgets, optimizing costs, forecasting revenue, or analyzing financial performance. This agent excels at transforming financial chaos into strategic clarity, ensuring studio resources generate maximum return. Examples:\n\n \nContext: Planning next quarter's development budget.

xbim08/awesome-claude-code-plugins · 56 tokens

legal-compliance-checker

Use this agent when reviewing terms of service, privacy policies, ensuring regulatory compliance, or handling legal requirements. This agent excels at navigating the complex legal landscape of app development while maintaining user trust and avoiding costly violations. Examples:\n\n \nContext: Launching app in…

xbim08/awesome-claude-code-plugins · 64 tokens

performance-benchmarker

Use this agent for comprehensive performance testing, profiling, and optimization recommendations. This agent specializes in measuring speed, identifying bottlenecks, and providing actionable optimization strategies for applications. Examples:\n\n \nContext: Application speed testing.

xbim08/awesome-claude-code-plugins · 52 tokens

project-shipper

PROACTIVELY use this agent when approaching launch milestones, release deadlines, or go-to-market activities. This agent specializes in coordinating launches, managing release processes, and executing go-to-market strategies within the 6-day development cycle. Should be triggered automatically when release dates are…

xbim08/awesome-claude-code-plugins · 436 tokens

experiment-tracker

PROACTIVELY use this agent when experiments are started, modified, or when results need analysis. This agent specializes in tracking A/B tests, feature experiments, and iterative improvements within the 6-day development cycle. Should be triggered automatically when experimental code paths or feature flags are…

xbim08/awesome-claude-code-plugins · 428 tokens