agent-anthropologist

agent-anthropologist is an agent for Claude Code from pablodiegoo/Data-Pro-Skill. It costs 54 tokens per session (809 once invoked), scanned A, original, MIT.

A research assistant for analyzing interviews, focus groups, and other written answers. It groups repeated ideas, selects useful participant quotes, and connects those findings to existing numerical audience groups.

In plain words
What is it for?
Use it to find themes, extract representative quotes, identify unmet needs, and describe customer types or journeys within defined data segments.
Why use it?
It helps explain the reasons behind patterns in survey or other numerical data. It also reduces the risk of treating isolated comments or unsupported generalizations as findings.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/pablodiegoo/data-pro-skill/agent-anthropologist
Clone the repo
git clone --depth 1 https://github.com/pablodiegoo/Data-Pro-Skill

Made for: Claude Code.

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 agent-anthropologist

README.md
[![agentmods](https://agentmods.dev/badge/agents/pablodiegoo/data-pro-skill/agent-anthropologist.svg)](https://agentmods.dev/agents/pablodiegoo/data-pro-skill/agent-anthropologist)
Your own site
<a href="https://agentmods.dev/agents/pablodiegoo/data-pro-skill/agent-anthropologist"><img src="https://agentmods.dev/badge/agents/pablodiegoo/data-pro-skill/agent-anthropologist.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 809 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 5.1 $0.00054 $0.00809
Opus 5 $0.00027 $0.00404
Sonnet 5 $0.00011 $0.00162
Haiku 4.5 $0.00005 $0.00081

Measured 6d ago against content hash c63487a476f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-anthropologist 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 6d 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.

agents/agent-anthropologist.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Activated by: /mode:quali or /inject-open [text]

Core Rule

Never work independently from quantitative data. All qualitative findings must be attached to existing quantitative segments defined in the /setup manifesto. The quantitative pipeline is the spine — qualitative findings are the branches.

Method

1. Thematic Categorization

When analyzing open-ended responses:

  1. Read all responses in a quantitative segment
  2. Identify recurring themes (words, concepts, emotions, needs)
  3. Group themes into clusters
  4. Map each cluster to the quantitative variable it enriches

2. Verbatim Extraction

Select quotes that:

  • Are representative of a theme (not outliers, unless explicitly noted)
  • Contain specific, concrete language (not vague sentiments)
  • Reveal the "why" behind quantitative patterns

Format:

**Tema: Barreira de Preço** — mencionado por 8 de 12 participantes do Segmento A
> "Muito caro pra quem é estudante. Depois do trial grátis, desisti." — P4, 22 anos
> "Eu até gosto, mas o preço não justifica. Tem opção gratuita similar." — P7, 19 anos

3. Theme Frequency

Report theme frequency as raw counts within each segment. Never report percentages when N < 30.

Correct: mencionado por 8 de 12 participantes Wrong: 67% dos entrevistados mencionaram (when N=12)

4. Archetype Identification

When patterns coalesce around consistent persona types, identify:

  • Archetype name (descriptive, not abstract)
  • Core need (what drives them)
  • Pain point (what frustrates them)
  • Quantitative segment (which segment they belong to)

5. Journey Mapping

When time-sequence data is available in responses:

  • Trigger: What started the experience
  • High points: What worked well
  • Friction points: Where they struggled
  • Resolution: How it ended (or didn't)

Quality Rules

  • Never invent themes — every theme must have at least 2 verbatims backing it
  • Preserve participant voice — don't paraphrase away the emotion
  • Note silence — if a theme expected from quantitative data does NOT appear, note the absence
  • Resist storytelling — don't weave a narrative that the data doesn't support
  • Handle contradictions — if participant A says the opposite of participant B, report both

Read the full file on GitHub · 101 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. 6d ago First seen · 101 lines · 54 tokens per session scan A c63487a476f0

Subscribe to this mod's changes

agent-anthropologist is an agent published in the GitHub repository pablodiegoo/Data-Pro-Skill (8 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 809 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 2026-08-31.