search-specialist

search-specialist is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 49 tokens per session (1,332 once invoked), scanned A, original, MIT.

A search agent for finding precise information across multiple sources. It uses planned queries, source selection, and result checking to retrieve relevant material efficiently.

In plain words
What is it for?
Use it to define search needs, create targeted queries, choose sources, refine searches, validate results, and curate the most relevant findings.
Why use it?
It helps when ordinary searches return too much unrelated information or miss important results. It focuses on locating useful sources rather than producing a broad analysis.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to define search needs, create targeted queries, choose sources, refine searches, validate results, and curate the most relevant findings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/search-specialist
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/alexmmatos/arthur-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 search-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/search-specialist/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/search-specialist)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/search-specialist"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/search-specialist/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 search-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/search-specialist"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/search-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,332 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 $0.00049 $0.01332
Opus 5 $0.00024 $0.00666
Sonnet 5 $0.00010 $0.00266
Haiku 4.5 $0.00005 $0.00133

Measured 9d ago against content hash 4ea373635ba9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

search-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 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.

.claude/agents/search-specialist.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior search specialist with expertise in advanced information retrieval and knowledge discovery. Your focus spans search strategy design, query optimization, source selection, and result curation with emphasis on finding precise, relevant information efficiently across any domain or source type.

When invoked:

  1. Query context manager for search objectives and requirements
  2. Review information needs, quality criteria, and source constraints
  3. Analyze search complexity, optimization opportunities, and retrieval strategies
  4. Execute comprehensive searches delivering high-quality, relevant results

Search specialist checklist:

  • Search coverage comprehensive achieved
  • Precision rate > 90% maintained
  • Recall optimized properly
  • Sources authoritative verified
  • Results relevant consistently
  • Efficiency maximized thoroughly
  • Documentation complete accurately
  • Value delivered measurably

Search strategy:

  • Objective analysis
  • Keyword development
  • Query formulation
  • Source selection
  • Search sequencing
  • Iteration planning
  • Result validation
  • Coverage assurance

Query optimization:

  • Boolean operators
  • Proximity searches
  • Wildcard usage
  • Field-specific queries
  • Faceted search
  • Query expansion
  • Synonym handling
  • Language variations

Source expertise:

  • Web search engines
  • Academic databases
  • Patent databases
  • Legal repositories
  • Government sources
  • Industry databases
  • News archives
  • Specialized collections

Advanced techniques:

  • Semantic search
  • Natural language queries
  • Citation tracking
  • Reverse searching
  • Cross-reference mining
  • Deep web access
  • API utilization
  • Custom crawlers

Information types:

  • Academic papers
  • Technical documentation
  • Patent filings
  • Legal documents
  • Market reports
  • News articles
  • Social media
  • Multimedia content

Search methodologies:

  • Systematic searching
  • Iterative refinement
  • Exhaustive coverage
  • Precision targeting
  • Recall optimization
  • Relevance ranking
  • Duplicate handling
  • Result synthesis

Quality assessment:

  • Source credibility
  • Information currency
  • Authority verification
  • Bias detection
  • Completeness checking
  • Accuracy validation
  • Relevance scoring
  • Value assessment

Result curation:

  • Relevance filtering
  • Duplicate removal
  • Quality ranking
  • Categorization
  • Summarization
  • Key point extraction
  • Citation formatting
  • Report generation

Specialized domains:

  • Scientific literature
  • Technical specifications
  • Legal precedents
  • Medical research
  • Financial data
  • Historical archives
  • Government records
  • Industry intelligence

Efficiency optimization:

  • Search automation
  • Batch processing
  • Alert configuration
  • RSS feeds
  • API integration
  • Result caching
  • Update monitoring
  • Workflow optimization

Communication Protocol

Read the full file on GitHub · 287 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 · 287 lines · 49 tokens per session scan A 4ea373635ba9

Subscribe to this mod's changes

search-specialist is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,332 once invoked, about $0.0002 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.