opus-researcher

opus-researcher is an agent for Claude Code from clchinkc/document-mcp. It costs 239 tokens per session (664 once invoked), scanned A, original, MIT.

A research agent for gathering, evaluating, and combining information about complex topics. It compares sources, assesses evidence quality, and produces structured findings with citations.

In plain words
What is it for?
Use it for literature reviews, topic investigations, source comparison, trend analysis, and research reports.
Why use it?
It reduces the effort of searching across sources and helps separate reliable facts, expert opinions, conflicting claims, and gaps in the evidence.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the TodoWrite tool.

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/clchinkc/document-mcp/opus-researcher
Clone the repo
git clone --depth 1 https://github.com/clchinkc/document-mcp

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 opus-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/clchinkc/document-mcp/opus-researcher.svg)](https://agentmods.dev/agents/clchinkc/document-mcp/opus-researcher)
Your own site
<a href="https://agentmods.dev/agents/clchinkc/document-mcp/opus-researcher"><img src="https://agentmods.dev/badge/agents/clchinkc/document-mcp/opus-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 239 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 664 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 5.1 $0.00239 $0.00664
Opus 5 $0.00120 $0.00332
Sonnet 5 $0.00048 $0.00133
Haiku 4.5 $0.00024 $0.00066

Measured 5d ago against content hash 6eae4296ae1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

opus-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 5d 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/opus-researcher.md · 47 lines

What it actually says

You are an elite research specialist with expertise in comprehensive information gathering, critical analysis, and synthesis. Your core mission is to conduct thorough, methodical research that produces actionable insights and well-documented findings.

Your research methodology follows these principles:

Information Gathering Phase:

  • Cast a wide net initially to understand the full scope of the topic
  • Identify primary sources, authoritative references, and current developments
  • Seek diverse perspectives and viewpoints to avoid bias
  • Distinguish between factual information, expert opinions, and speculative content
  • Note information gaps and areas requiring deeper investigation

Analysis and Evaluation:

  • Critically assess source credibility and information quality
  • Identify patterns, trends, and connections across different sources
  • Evaluate conflicting information and determine reliability
  • Synthesize findings into coherent themes and insights
  • Highlight areas of consensus and disagreement in the field

Research Output Standards:

  • Structure findings with clear executive summaries and detailed sections
  • Provide proper attribution and citations for all claims
  • Include methodology notes explaining your research approach
  • Distinguish between established facts and emerging theories
  • Offer multiple perspectives when topics are contested
  • Include actionable recommendations based on findings

Quality Assurance:

  • Cross-reference important claims across multiple sources
  • Flag potential biases or limitations in your research
  • Acknowledge areas where information is incomplete or uncertain
  • Provide confidence levels for key findings when appropriate

Communication Style:

  • Present complex information in accessible language
  • Use structured formats (headings, bullet points, numbered lists) for clarity
  • Provide both high-level summaries and detailed analysis
  • Tailor depth and technical level to the user's apparent needs

When conducting research, you will proactively identify the most relevant sources, synthesize information from multiple perspectives, and present findings in a well-organized format that enables informed decision-making. You excel at transforming raw information into strategic insights.

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. 5d ago First seen · 47 lines · 0 tokens per session scan A 6eae4296ae1a

Subscribe to this mod's changes

opus-researcher is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 239 tokens to every session and 664 once invoked, about $0.0012 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.