research-agent

research-agent is an agent for Claude Code from PedroMeloOfficial/Youtube-Agent-Matrix. It costs 82 tokens per session (1,683 once invoked), scanned A, original, MIT.

A research workflow that builds a sourced dossier for a video topic. It records verified facts, overlooked background, existing coverage in two languages, open angles, current discussion, timing hooks, and useful visuals.

In plain words
What is it for?
Use it to investigate a topic, identify what is already known or covered, find gaps, assess current discussion, and prepare evidence for a video script.
Why use it?
It separates fact-checking and coverage research from idea generation, so later script claims can be traced back to documented sources.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the youtube-agent-matrix plugin — 1 skill, 1 command, 14 agents shipped together

Good fit Use it to investigate a topic, identify what is already known or covered, find gaps, assess current discussion, and prepare evidence for a video script.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pedromeloofficial/youtube-agent-matrix/research-agent
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/PedroMeloOfficial/Youtube-Agent-Matrix

Made for: Claude Code.

Or install youtube-agent-matrix, the plugin that ships this one along with the rest of its 1 skill, 1 command, 14 agents.

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 research-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/research-agent/github.svg)](https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/research-agent)
Your own site
<a href="https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/research-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/research-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for research-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/pedromeloofficial/youtube-agent-matrix/research-agent"><img src="https://agentmods.dev/badge/agents/pedromeloofficial/youtube-agent-matrix/research-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,683 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 $0.00082 $0.01683
Opus 5 $0.00041 $0.00842
Sonnet 5 $0.00016 $0.00337
Haiku 4.5 $0.00008 $0.00168

Measured 12d ago against content hash 5a0fe242d067, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

research-agent 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 12d 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/research-agent.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent

You supply the ammunition. Every fact the script agent asserts on camera traces back to this file, so anything wrong here becomes the creator's error in front of their audience.

You do not propose video ideas. That is the ideation agent's job. You establish what is true, what has already been said, and what has not.


Inputs you will receive

Input Use
OUTPUT LANGUAGE The language every deliverable is written in. Non-negotiable.
_handoff.md Decisions already made and rejected at earlier gates — read it before writing anything
The topic or subject What you are researching
workspace/channel-profile.md Audience knowledge level, pillars, constraints, spoiler policy
templates/channel-types/<archetype>.md §1 channel DNA, §3 length band — what depth is usable
references/benchmarks.md Any platform number you cite
Creator's verbatim words Angles they want, angles they refuse

If the topic is broad ("this whole subject"), narrow it once, explicitly, to what one video can carry at the archetype's length, and say which narrowing you chose.


What the dossier contains

1 · Verified facts

The substance: names, dates, numbers, sequence of events, technical specifics. Every claim carries a source URL on the same line. Prefer primary sources — official documentation, filings, transcripts, the creator's own statements, the original release — over aggregators recycling each other.

2 · The decisions layer

The part most coverage skips: documented decisions, constraints, reversals, what was tried first and abandoned, who pushed for what. Interviews, commentary tracks, developer notes, postmortems, court records, archived posts. This layer is usually where the video's actual value lives — the surface facts are already on ten channels.

3 · What already exists

Search in OUTPUT LANGUAGE and in English. Both, always. A framing that saturates one language and is absent from the other is a real opening, and you cannot see it from one side.

Read the full file on GitHub · 155 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. 12d ago First seen · 155 lines · 82 tokens per session scan A 5a0fe242d067

Subscribe to this mod's changes

research-agent is an agent published in the GitHub repository PedroMeloOfficial/Youtube-Agent-Matrix (6 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 1,683 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

blog-researcher

Research specialist for blog content. Finds current statistics (2025-2026), verifies sources against tier 1-3 quality standards, discovers Pixabay/Unsplash/Pexels images, and identifies competitive content gaps. Invoked for statistic research, image discovery, and competitive analysis tasks during blog writing…

AgriciDaniel/claude-blog · 66 tokens

blog-reviewer

Quality assessment specialist for blog posts. Runs the full 5-category, 100-point scoring system, identifies issues by severity, checks for AI editorial style diagnostics, validates source quality, and flags unsupported factual or first-hand claims. Invoked for quality review tasks during blog workflows.

AgriciDaniel/claude-blog · 59 tokens

blog-writer

Content generation specialist for blog posts. Writes optimized articles with answer-first formatting, proper heading hierarchy, sourced statistics, and natural readability. Follows the 6 pillars of dual optimization. Invoked for content writing and rewriting tasks during blog workflows.

AgriciDaniel/claude-blog · 52 tokens

claude-blog-secretary

The owner's dedicated Claude Blog agent, grounded in the Claude Blog Brain at . Use for any blog-content work - writing and rewriting for Google rankings and AI citations, E-E-A-T, GEO and AEO, schema, topic clusters, briefs and outlines, editorial strategy, multilingual publishing, the FLOW framework, factchecking…

AgriciDaniel/claude-blog · 0 tokens

blog-cluster-curator

Topic Clusters curator for the Claude Blog Brain. Maintains and answers from the Topic Clusters theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for semantic topic clusters, hub-and-spoke architecture, internal linking, and cannibalization.

AgriciDaniel/claude-blog · 64 tokens

blog-data-curator

Data Integrations curator for the Claude Blog Brain. Maintains and answers from the Data Integrations theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for GSC, GA4, PageSpeed, CrUX, and NLP integrations plus content-decay detection.

AgriciDaniel/claude-blog · 66 tokens