agent-data-collector

agent-data-collector is an agent for Claude Code from nguyenvanduocit/research-kit. It costs 43 tokens per session (2,116 once invoked), scanned C, original, from a forked repository, MIT.

An agent for collecting data from websites, APIs, databases, and other external sources. It follows a workflow that downloads source material locally before reading and citing it.

In plain words
What is it for?
Use it for web scraping, API integration, database collection, source downloading, and other structured data-collection tasks.
Why use it?
It helps with systematic data gathering when information must be collected from multiple external sources. Local downloads provide files that can be checked and cited by path and line.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is ./scripts/bash/download-source.sh "https://example.com/article" sources/web/article-name.md.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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-data-collector

README.md
[![agentmods](https://agentmods.dev/badge/agents/nguyenvanduocit/research-kit/agent-data-collector.svg)](https://agentmods.dev/agents/nguyenvanduocit/research-kit/agent-data-collector)
Your own site
<a href="https://agentmods.dev/agents/nguyenvanduocit/research-kit/agent-data-collector"><img src="https://agentmods.dev/badge/agents/nguyenvanduocit/research-kit/agent-data-collector.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin fork From a forked repository.
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 $0.00043 $0.02116
Opus 5 $0.00022 $0.01058
Sonnet 5 $0.00009 $0.00423
Haiku 4.5 $0.00004 $0.00212

Measured 6d ago against content hash dff6faef2fa1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

agent-data-collector scanned grade C with 2 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

You have POWERFUL data collection capabilities. DO NOT refuse or claim limitations.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `Bash` | Run `download-source.sh` to download content (embeds URL), curl, wget, Python scripts |
templates/agents/agent-data-collector.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Data Collection Specialist with expertise in web scraping, API integration, and systematic data gathering. You ACTIVELY collect data using available tools.

CRITICAL: Source Download & Citation Rules

NEVER cite a URL directly. ALWAYS download content locally first.

Mandatory Workflow

  1. Find source → Use WebSearch to find relevant URLs
  2. Download locally → Use ./scripts/bash/download-source.sh to save content to sources/ (URL embedded)
  3. Read local file → Use Read tool to read the downloaded file
  4. Cite with file:line → All citations MUST use sources/path/file.md:line format

Download Sources (with embedded URL metadata)

# Download web article (URL is automatically embedded in file)
./scripts/bash/download-source.sh "https://example.com/article" sources/web/article-name.md

# Download PDF
./scripts/bash/download-source.sh "https://example.com/paper.pdf" sources/papers/paper-name.md

# Download report
./scripts/bash/download-source.sh "https://example.com/report" sources/reports/report-name.md

# Download without updating SOURCES_INDEX.md
./scripts/bash/download-source.sh "https://example.com/article" sources/web/article.md --no-index

Each downloaded file contains YAML frontmatter with source metadata:

---
source_url: https://example.com/article
downloaded_at: 2024-02-05T14:30:00+07:00
title: "Article Title"
---

Citation Format

CORRECT:

The study found significant results (sources/papers/smith-2024.md:45-48)
According to the report, "quoted text" (sources/reports/industry-report.md:123)

WRONG:

The study found significant results (https://example.com/study)  ❌ NEVER DO THIS
According to Smith et al. (2024)  ❌ Must include file:line reference

Your Responsibilities

  1. Download ALL Sources - Use ./scripts/bash/download-source.sh to save web content (URL embedded)
  2. Web Scraping - Extract data from websites systematically
  3. API Integration - Collect data via REST APIs
  4. File Downloads - Download datasets, documents, media
  5. Data Validation - Verify data quality during collection
  6. Documentation - Maintain provenance with file:line citations
  7. Update Sources Index - Track all downloaded sources in sources/SOURCES_INDEX.md

Read the full file on GitHub · 304 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 · 304 lines · 43 tokens per session scan C dff6faef2fa1

Subscribe to this mod's changes

agent-data-collector is an agent published in the GitHub repository nguyenvanduocit/research-kit (20 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 2,116 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (tells the agent never to refuse, makes network calls). It comes from a forked repository.