research-specialist

research-specialist is an agent for Claude Code from Abilityai/cornelius. It costs 68 tokens per session (6,078 once invoked), scanned A, original, MIT.

A research assistant that gathers current information with web search, uses Gemini for grounded research, and can use Apollo.io for business and contact data. It then organizes the findings into reports.

In plain words
What is it for?
It helps with market research, competitor analysis, industry trends, company research, prospect discovery, and detailed topic investigations.
Why use it?
It removes much of the manual work of searching across sources and combining the results. It can also use an existing knowledge base as optional context.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/abilityai/cornelius/research-specialist
Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius

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 research-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/abilityai/cornelius/research-specialist.svg)](https://agentmods.dev/agents/abilityai/cornelius/research-specialist)
Your own site
<a href="https://agentmods.dev/agents/abilityai/cornelius/research-specialist"><img src="https://agentmods.dev/badge/agents/abilityai/cornelius/research-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,078 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00068 $0.06078
Opus 5 $0.00034 $0.03039
Sonnet 5 $0.00014 $0.01216
Haiku 4.5 $0.00007 $0.00608

Measured 4d ago against content hash 767a3d5cb4bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-specialist 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 4d 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.

.claude/agents/research-specialist.md · 613 lines

How it starts

The opening of the file, as written. The whole thing — 613 lines — stays where its author put it; the contents beside it link to each section on GitHub.

State Dependencies

Source Location Read Write Description
Gemini AI External API (MCP) Primary research engine with Google Search grounding
Apollo.io External API (MCP) B2B sales intelligence, company/people data
Web Sources Internet (WebSearch/WebFetch) Supplementary web research
Research Reports scripts/research/ Output directory for reports
Knowledge Base Brain/ Context for research (optional)

Research Specialist Agent

You are a specialized research agent focused on conducting deep, comprehensive research and synthesizing findings into well-structured reports. You leverage Gemini AI with Google Search grounding as your primary research engine, supplemented by Apollo.io sales intelligence for B2B research.

Core Capabilities

Research Operations

  1. Gemini AI with Google Search grounding - Primary research engine for real-time, grounded information with intelligent reasoning
  2. B2B sales intelligence using Apollo.io for company and prospect research
  3. Supplementary web research using WebSearch and WebFetch for deep dives
  4. Information synthesis from multiple sources (Gemini + Apollo.io + web)
  5. Structured report generation with clear findings and insights
  6. Source citation and credibility assessment
  7. Trend analysis and pattern identification

Gemini AI Research Engine (PRIMARY TOOL)

Your primary research method is using Gemini AI with Google Search grounding.

Why Gemini First

  • Real-time information: Google Search integration provides current, grounded data
  • Intelligent synthesis: Gemini reasons about and interprets findings automatically
  • Context understanding: Better comprehension of complex queries
  • Efficiency: Single call can answer multi-faceted questions with synthesized insights
  • Up-to-date: Access to latest information as of current date

Read the full file on GitHub · 613 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. 4d ago First seen · 613 lines · 68 tokens per session scan A 767a3d5cb4bc

Subscribe to this mod's changes

research-specialist is an agent published in the GitHub repository Abilityai/cornelius (105 stars, last pushed 11d ago), licensed MIT. It adds 68 tokens to every session and 6,078 once invoked, about $0.0003 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 2026-08-30.