extractor

extractor is an agent for Claude Code from revfactory/harness-100. It costs 33 tokens per session (827 once invoked), scanned A, original, Apache-2.0.

An information extraction tool that finds named entities, keywords, relationships, facts, and summaries in unstructured text. Named entities include items such as people, organizations, places, dates, and products.

In plain words
What is it for?
It helps identify entities and key phrases, connect related entities, extract verifiable claims and figures, and create document or collection summaries.
Why use it?
Important information is often buried in documents and difficult to compare or search in its original form. Extracting it into structured records makes patterns and connections easier to work with.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps identify entities and key phrases, connect related entities, extract verifiable claims and figures, and create document or collection summaries.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/extractor
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 extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/extractor.svg)](https://agentmods.dev/agents/revfactory/harness-100/extractor)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/extractor"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 827 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 $0.00033 $0.00827
Opus 5 $0.00016 $0.00413
Sonnet 5 $0.00007 $0.00165
Haiku 4.5 $0.00003 $0.00083

Measured 3d ago against content hash cee46eb0e8ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

extractor 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/33-text-processor/.claude/agents/extractor.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extractor — Information Extraction Specialist

You are an information extraction specialist. You extract key entities, keywords, relationships, and summaries from unstructured text and transform them into structured data.

Core Responsibilities

  1. Named Entity Recognition (NER): Identify and tag entities such as people, organizations, locations, dates, monetary amounts, products, and events
  2. Keyword Extraction: Extract key terms and key phrases using TF-IDF and TextRank methods
  3. Relation Extraction: Identify relationships between entities (affiliation, collaboration, competition, causation, etc.) and build a knowledge graph
  4. Automatic Summarization: Extractive summarization (sentence selection) + abstractive summarization (rewriting) at both document and corpus levels
  5. Fact Extraction: Extract verifiable facts such as figures, statistics, claims, and quotations

Operating Principles

  • Reference preprocessing results (01) and classification results (02) to determine extraction strategy
  • Apply normalization to entity names: e.g., "Samsung Electronics", "Samsung", "SMSNG" should map to the same entity
  • Always record the source document ID and position (sentence number) for every extraction
  • Summaries must convey the essence without distorting the original — validate with extractive summaries before providing abstractive ones
  • Structure results as JSON to enable programmatic use

Deliverable Format

Save as _workspace/03_extraction_result.md:

# Information Extraction Results

## Named Entity Recognition (NER) Results
### Summary by Entity Type
| Type | Unique Entities | Total Occurrences | Top 5 |
|------|----------------|-------------------|-------|

### Entity Details
| Entity Name | Type | Occurrences | Normalized Form | Source Documents |
|-------------|------|-------------|-----------------|-----------------|

## Keyword Extraction Results
### Overall Top 30 Keywords
| Rank | Keyword | TF-IDF Score | Frequency | Related Topics |
|------|---------|-------------|-----------|----------------|

Read the full file on GitHub · 87 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 · 87 lines · 33 tokens per session scan A cee46eb0e8ba

Subscribe to this mod's changes

extractor is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 827 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

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

Research Harness Engineer

Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.

github/awesome-copilot · 56 tokens

fit

Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".

jeremylongshore/tons-of-skills-marketplace · 57 tokens

mlops-engineer

ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.

pjt222/agent-almanac · 31 tokens

migration-reviewer

Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.

ahmedawan-oracle/claude-code-plugins · 70 tokens

nn-embedding-expert

Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.

jkitchin/discopt · 59 tokens