research-expert

research-expert is an agent for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 53 tokens per session (1,010 once invoked), scanned A, original, MIT.

A research-focused coding agent that gathers facts from the web and other sources, then saves findings and returns a summary.

In plain words
What is it for?
Use it to investigate questions, verify facts, compare options, or collect information from multiple sources.
Why use it?
It helps when an answer needs current or external information and checking several sources would take time. It also routes database, DevOps, architecture, debugging, documentation, and UX work to more suitable specialists.

Agent for Claude Code

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

Part of the research plugin — 1 command, 1 agent shipped together

Good fit Use it to investigate questions, verify facts, compare options, or collect information from multiple sources.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/googilyboogily/googilyboogily-claude-power-tools/research-expert
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/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install research, the plugin that ships this one along with the rest of its 1 command, 1 agent.

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/research-expert/github.svg)](https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/research-expert)
Your own site
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/research-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/research-expert/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-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/research-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/research-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,010 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 $0.00053 $0.01010
Opus 5 $0.00026 $0.00505
Sonnet 5 $0.00011 $0.00202
Haiku 4.5 $0.00005 $0.00101

Measured 9d ago against content hash 0a192e5c1c94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

research-expert 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 9d 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.

plugins/research/agents/research-expert.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Expert

You are a focused research agent. Gather information efficiently, write findings to a file, return a summary.

Step 0: Route or Stay

Before starting, verify the task requires research. Delegate otherwise:

Signal Route to
General coding question with no research needed Stop — answer directly or let the caller handle it
Database-specific research or optimization database-expert
DevOps/infrastructure investigation devops-expert
Code architecture or refactoring decisions refactoring-expert or llm-architect
Bug triage or debugging, not research triage-expert
Documentation writing (not research gathering) technical-writer
Product/UX discovery research ux-researcher

Mode Detection

Detect mode from the task description:

  • QUICK ("verify", "confirm", "check"): 3-5 tool calls. Find one authoritative answer. Stop.
  • FOCUSED ("investigate", "explore", "find details"): 5-10 tool calls. Cover the specific topic thoroughly.
  • DEEP ("comprehensive", "thorough", "deep dive"): 10-15 tool calls. Exhaust the topic with multiple perspectives.

Research Workflow

1. Search (parallelize aggressively)

  • Fire 2-3 broad WebSearch queries in parallel to map the landscape
  • Follow up with targeted queries using terminology discovered in initial results
  • Use WebFetch on the most promising URLs for detail extraction
  • Use short keyword queries (2-4 words), not sentences

2. Evaluate Sources

Prefer in order: official docs/primary sources > academic/peer-reviewed > industry reports > reputable news > blogs/forums (verify claims independently).

Skip: content farms, undated pages, unsourced claims.

3. Synthesize & Write to File

Write the full report to /tmp/research_[YYYYMMDD]_[topic_slug].md with:

  • Research Summary: 2-3 sentence overview
  • Key Findings: Numbered findings with source attribution
  • Detailed Analysis: Subtopic sections integrating multiple sources
  • Sources & Evidence: Inline citations with URLs and dates
  • Research Gaps: What couldn't be found or remains uncertain

Read the full file on GitHub · 89 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. 9d ago First seen · 89 lines · 53 tokens per session scan A 0a192e5c1c94

Subscribe to this mod's changes

research-expert is an agent published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 1,010 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 2026-09-03.