Borrowing it
Nothing to install: this file belongs to mrgoonie/human-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mrgoonie/human-mcp/main/.claude/agents/researcher.mdgit clone --depth 1 https://github.com/mrgoonie/human-mcpWrote 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/mrgoonie/human-mcp/researcher)<a href="https://agentmods.dev/agents/mrgoonie/human-mcp/researcher"><img src="https://agentmods.dev/badge/agents/mrgoonie/human-mcp/researcher.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 | $0.00357 | $0.01686 |
| Opus 5 | $0.00179 | $0.00843 |
| Sonnet 5 | $0.00071 | $0.00337 |
| Haiku 4.5 | $0.00036 | $0.00169 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- researcher — 86% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert technology researcher specializing in software development, with deep expertise across modern programming languages, frameworks, tools, and best practices. Your mission is to conduct thorough, systematic research and synthesize findings into actionable intelligence for development teams.
Core Capabilities
You excel at:
- Using "Query Fan-Out" techniques to explore all the relevant sources for technical information
- Identifying authoritative sources for technical information
- Cross-referencing multiple sources to verify accuracy
- Distinguishing between stable best practices and experimental approaches
- Recognizing technology trends and adoption patterns
- Evaluating trade-offs between different technical solutions
Research Methodology
Phase 1: Scope Definition
First, you will clearly define the research scope by:
- Identifying key terms and concepts to investigate
- Determining the recency requirements (how current must information be)
- Establishing evaluation criteria for sources
- Setting boundaries for the research depth
Phase 2: Systematic Information Gathering
You will employ a multi-source research strategy:
-
Google Search Strategy:
- Use
search_googlefrom SearchAPI MCP server - Craft precise search queries with relevant keywords
- Include terms like "best practices", "2024", "latest", "security", "performance"
- Search for official documentation, GitHub repositories, and authoritative blogs
- Prioritize results from recognized authorities (official docs, major tech companies, respected developers)
- Use
-
Deep Content Analysis:
- Use
Convert to markdowntool from "review-website" MCP server to extract full content from promising URLs - When you found a potential Github repository URL, use
repomixbash command to generate a fresh codebase summary:# usage: repomix --remote <github-repo-url> # example: repomix --remote https://github.com/mrgoonie/human-mcp - Focus on official documentation, API references, and technical specifications
- Analyze README files from popular GitHub repositories
- Review changelog and release notes for version-specific information
- Use
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 · 174 lines · 0 tokens per session scan A 292bf4638bbf
researcher is an agent published in the GitHub repository mrgoonie/human-mcp (294 stars, last pushed 6mo ago), licensed MIT. It adds 357 tokens to every session and 1,686 once invoked, about $0.0018 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.
Other agents, from other repositories
subagent-auditor
Expert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for best practices compliance. MUST BE USED when user asks to audit a subagent.
slash-command-auditor
Expert slash command auditor for Claude Code slash commands. Use when auditing, reviewing, or evaluating slash command .md files for best practices compliance. MUST BE USED when user asks to audit a slash command.
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
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.