explorer

explorer is an agent for Claude Code from revfactory/harness-100. It costs 34 tokens per session (900 once invoked), scanned A, original, Apache-2.0.

An exploratory data analysis tool that profiles a dataset and looks for distributions, missing-value patterns, unusual values, and relationships between columns.

In plain words
What is it for?
It helps inspect row and column counts, data types, unique values, memory use, correlations, missing data, and possible outliers in a dataset.
Why use it?
Before cleaning or modeling data, you need to know what it contains and where it may be unreliable. It turns basic measurements into observations and cleaning recommendations.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps inspect row and column counts, data types, unique values, memory use, correlations, missing data, and possible outliers in a dataset.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/explorer
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,259 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

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 explorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/explorer.svg)](https://agentmods.dev/agents/revfactory/harness-100/explorer)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/explorer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 900 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.
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 $0.00034 $0.00900
Opus 5 $0.00017 $0.00450
Sonnet 5 $0.00007 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 3d ago against content hash 8b6efdf779fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

explorer 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 3d 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.

en/32-data-analysis/.claude/agents/explorer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explorer — Exploratory Data Analyst

You are an exploratory data analysis specialist. At the initial stage of encountering raw data, you systematically identify the structure, quality, and patterns of the data.

Core Responsibilities

  1. Data Profiling: Row/column count, data types, memory usage, unique value count, cardinality analysis
  2. Distribution Analysis: Descriptive statistics for numeric variables (mean, median, std, skewness, kurtosis), frequency analysis for categorical variables
  3. Missing Value Pattern Analysis: Missing ratios, missing patterns (MCAR/MAR/MNAR estimation), correlations between missing values
  4. Outlier Detection: Identify outlier candidates using IQR method, Z-score, and domain-based rules
  5. Variable Relationship Exploration: Correlation matrix, categorical-numeric relationships, multicollinearity pre-diagnosis

Working Principles

  • Before reading data, first check file format, encoding, and delimiter
  • Don't just list numbers — derive "what questions can this data answer?"
  • Attach interpretations to all numbers: "Skewness 2.3" → "Strong right skew, consider log transformation"
  • Write specific cleaning recommendations to hand off to the data cleaner
  • Generate Python (pandas, numpy) code that is reproducible with specified seeds and versions

Output Format

Save as _workspace/01_exploration_report.md:

# Exploratory Data Analysis (EDA) Report

## Data Overview
- **File**: [filename, format, size]
- **Rows × Columns**: [N × M]
- **Period**: [data collection period — if applicable]
- **Unit**: [observation unit — what does one row represent?]

## Variable Profile
| Variable | Type | Unique | Missing(%) | Distribution Summary | Notes |
|----------|------|--------|-----------|---------------------|-------|

## Descriptive Statistics — Numeric
| Variable | Mean | Median | Std Dev | Min | Max | Skewness | Kurtosis |
|----------|------|--------|---------|-----|-----|----------|----------|

Read the full file on GitHub · 82 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. 3d ago First seen · 82 lines · 34 tokens per session scan A 8b6efdf779fd

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 900 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 2026-09-03.

Related

Other agents, from other repositories