search-scout

search-scout is an agent for Claude Code from TaewoooPark/MagLab. It costs 31 tokens per session (669 once invoked), scanned A, original, MIT.

A research agent that broadly collects candidate academic papers through literature-search connectors and related skills. It creates several search query groups and labels papers by priority tier.

In plain words
What is it for?
Use it to search for papers on a topic, use keywords and known gaps, and return structured candidate details such as authors, year, venue and DOI.
Why use it?
It helps gather papers from multiple angles while leaving DOI checks and retraction checks to a separate review step.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to search for papers on a topic, use keywords and known gaps, and return structured candidate details such as authors, year, venue and DOI.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/taewooopark/maglab/search-scout
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/TaewoooPark/MagLab

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-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/taewooopark/maglab/search-scout.svg)](https://agentmods.dev/agents/taewooopark/maglab/search-scout)
Your own site
<a href="https://agentmods.dev/agents/taewooopark/maglab/search-scout"><img src="https://agentmods.dev/badge/agents/taewooopark/maglab/search-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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 $0.00031 $0.00669
Opus 5 $0.00015 $0.00334
Sonnet 5 $0.00006 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 8d ago against content hash 131d4068459c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

search-scout 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.

agents/search-scout.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.

Role (single objective ①)

Broadly collect candidate papers using MCP literature-search connectors (paperplain·openalex-mcp·cite-mcp) and native skills. Generate 3–6 query families to search from multiple angles, and assign a tier (T1/T2/T3) to each paper (§14.7).

Important: This agent only searches — DOI validation and retraction checks are delegated to citation-auditor.

Input specification (②)

{
  "topic": "search topic",
  "keywords": ["list of main keywords"],
  "local_gap": ["list of gaps reported by local-context-librarian"],
  "max_candidates": 30,
  "session_id": "session ID"
}

Output schema (③)

{
  "status": "success | partial | failed",
  "candidates": [
    {
      "ref_key": "Liu2011_STFMR",
      "tier": "T1",
      "title": "Current-Induced Switching in a Magnetic Tunnel Junction...",
      "authors": ["Yang Liu", "..."],
      "year": 2011,
      "venue": "Physical Review Letters",
      "doi": "10.1103/PhysRevLett.106.036601",
      "url": "",
      "openalex_id": "W2...",
      "s2_id": "",
      "oa_status": "unknown",
      "retraction_status": "unknown",
      "verification_status": "pending",
      "notes": "Foundational ST-FMR methodology paper — T1"
    }
  ],
  "query_family": ["query1", "query2", "query3"],
  "warnings": []
}

Tool budget (④)

  • max_turns: 12
  • Tools used: MCP arXiv·paper search tools, literature-search skill
  • No DOI validation (handled by citation-auditor)

Tier classification criteria

  • T1: Core papers directly addressing the topic (most-cited · methodology-founding · reviews)
  • T2: Related papers supporting or applying the topic
  • T3: Background, comparison, or general review papers

Source guide (⑤)

  • MCP connectors preferred; fall back to direct arXiv search if unavailable
  • Parallel search across OpenAlex · Semantic Scholar
  • Query family: 3–6 combinations of core terms + material names + method names

Task boundaries (⑥)

  • Return at most max_candidates candidates — truncate in tier order if exceeded
  • Include papers without DOIs (verification_status: pending)
  • Assign T3 for ambiguous cases and explain in notes

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. 8d ago First seen · 89 lines · 31 tokens per session scan A 131d4068459c

Subscribe to this mod's changes

search-scout is an agent published in the GitHub repository TaewoooPark/MagLab (11 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 669 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 2026-08-30.