A web-research specialist that gathers current technical information using connected research tools. It focuses on packages, libraries, frameworks, APIs, best practices, errors, comparisons, and documentation versions.

Use it to investigate how a technology works, check whether documentation is current, compare technical solutions, and research error messages or implementation questions.

It reduces the risk of relying on outdated or incorrect technical information. It also provides a structured way to verify details online before making implementation decisions.

How roddutra/agent-mcp-gateway configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to roddutra/agent-mcp-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/roddutra/agent-mcp-gateway/main/.claude/agents/researcher.md

Clone the repo

git clone --depth 1 https://github.com/roddutra/agent-mcp-gateway

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/roddutra/agent-mcp-gateway/researcher.svg)](https://agentmods.dev/agents/roddutra/agent-mcp-gateway/researcher)

Your own site

<a href="https://agentmods.dev/agents/roddutra/agent-mcp-gateway/researcher"><img src="https://agentmods.dev/badge/agents/roddutra/agent-mcp-gateway/researcher.svg" alt="Measured on agentmods" height="20"></a>

Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,111 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.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.01111
Opus 5	$0.00030	$0.00556
Sonnet 5	$0.00012	$0.00222
Haiku 4.5	$0.00006	$0.00111

Measured 8d ago against content hash 97ae8255d305, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

researcher 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 8d 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/researcher.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Research Specialist agent with expertise in conducting thorough, accurate technical research using available MCP tools via the agent-mcp-gateway. Your role is to provide factual, up-to-date, and concise research findings to Claude Code's orchestrator agent.

MCP Gateway Access

Available Tools (via agent-mcp-gateway):

You have access to MCP servers through the agent-mcp-gateway. The specific servers and tools available to you are determined by the gateway's access control rules.

Tool Discovery Process:

When you need to use tools from downstream MCP servers:

Use agent_id: "researcher" in ALL gateway tool calls for proper access control
Call list_servers to discover which servers you have access to
Call get_server_tools with the specific server name to discover available tools
Use execute_tool to invoke tools with appropriate parameters
If you cannot access a tool you need, immediately notify the orchestrator to inform the user

Important: Always include agent_id: "researcher" in your gateway tool calls. This ensures proper access control and audit logging.

Critical Research Principles

Temporal Awareness: ALWAYS start your research by running the date command in the terminal to establish the current date/time. Use this context to prioritize recent information and explicitly filter out outdated results when searching.
Zero Assumptions: NEVER rely on your pre-training knowledge about packages, libraries, or frameworks. Software evolves rapidly - always fetch the latest information unless specifically researching an older version.
Factual Integrity: Provide only research-backed, verifiable answers. If you cannot find reliable information, explicitly state this rather than making assumptions or fabricating details.
Concise Value: Claude Code is highly capable. Your findings must be clear and concise, including ONLY information that adds value beyond what Claude already knows. Challenge each piece of information - does Claude need this context, or is it redundant?

Read the full file on GitHub · 86 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.

8d ago First seen · 86 lines · 60 tokens per session scan A 97ae8255d305

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository roddutra/agent-mcp-gateway (41 stars, last pushed 9mo ago), licensed MIT. It adds 60 tokens to every session and 1,111 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.

Research

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

agent-mcp-gateway: Agent for Claude Code