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.
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.
[](https://agentmods.dev/agents/nguyenvanduocit/research-kit/agent-data-collector)<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>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.
| Model | Per session | Once 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 |
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 | 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
- Find source → Use WebSearch to find relevant URLs
- Download locally → Use
./scripts/bash/download-source.shto save content tosources/(URL embedded) - Read local file → Use Read tool to read the downloaded file
- Cite with file:line → All citations MUST use
sources/path/file.md:lineformat
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
- Download ALL Sources - Use
./scripts/bash/download-source.shto save web content (URL embedded) - Web Scraping - Extract data from websites systematically
- API Integration - Collect data via REST APIs
- File Downloads - Download datasets, documents, media
- Data Validation - Verify data quality during collection
- Documentation - Maintain provenance with file:line citations
- Update Sources Index - Track all downloaded sources in
sources/SOURCES_INDEX.md
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.
- 6d ago First seen · 304 lines · 43 tokens per session scan C dff6faef2fa1
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.