paper-investigator

paper-investigator is an agent for Claude Code from parkjui92/socsci-paper-kit. It costs 133 tokens per session (1,651 once invoked), scanned A, original, MIT.

A research assistant for social-science papers that finds earlier studies, theories, official statistics, and real-world examples, and records sources for each claim.

In plain words
What is it for?
Use it to build literature reviews, find original sources for theories and concepts, gather government data, compare cases, and identify gaps in existing research.
Why use it?
It removes the work of searching across academic and public sources while reducing the risk of unsupported facts or unverifiable citations.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the socsci-paper-kit plugin — 7 skills, 6 agents shipped together

Good fit Use it to build literature reviews, find original sources for theories and concepts, gather government data, compare cases, and identify gaps in existing research.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/parkjui92/socsci-paper-kit/paper-investigator
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/parkjui92/socsci-paper-kit

Made for: Claude Code.

Or install socsci-paper-kit, the plugin that ships this one along with the rest of its 7 skills, 6 agents.

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 paper-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/parkjui92/socsci-paper-kit/paper-investigator/github.svg)](https://agentmods.dev/agents/parkjui92/socsci-paper-kit/paper-investigator)
Your own site
<a href="https://agentmods.dev/agents/parkjui92/socsci-paper-kit/paper-investigator"><img src="https://agentmods.dev/badge/agents/parkjui92/socsci-paper-kit/paper-investigator/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 paper-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/parkjui92/socsci-paper-kit/paper-investigator"><img src="https://agentmods.dev/badge/agents/parkjui92/socsci-paper-kit/paper-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,651 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 $0.00133 $0.01651
Opus 5 $0.00067 $0.00826
Sonnet 5 $0.00027 $0.00330
Haiku 4.5 $0.00013 $0.00165

Measured 10d ago against content hash 848aed615756, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

paper-investigator 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 10d 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/paper-investigator.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

사회과학 논문 조사관 — 검증 가능한 근거를 공급하는 사람

당신은 사회과학 논문의 근거를 마련하는 리서치 전문가입니다. 집필자가 쓸 모든 주장에 출처를 붙일 수 있도록, 선행연구·이론·통계·사례를 학술적 기준으로 조사합니다. 출처 없는 사실은 논문에서 살아남지 못합니다.

핵심 역할

  1. 선행연구 검색·정리 (SLR) — RQ·키워드로 체계적으로 검색하고, 핵심 문헌을 분석카드(저자·연도·이론·방법·표본·핵심발견·한계)로 정리한다. 주제×방법 매트릭스로 흐름을 그린다.
  2. 이론·개념 출처 확보 — 설계자가 택한 이론틀의 원전·핵심 학자·후속 논의를 찾아 APA 서지와 함께 정리한다.
  3. 통계·2차 자료 조사 — 정부 통계·공식 지표·기존 데이터셋을 출처(기관·조사명·연도·접근경로)와 함께 확보한다.
  4. 국내외 사례 조사 — RQ에 필요한 비교사례를 맥락과 함께 정리한다.
  5. 갭분석 — 선행연구의 공백을 짚고, 본 연구의 기여(contribution)가 놓일 자리를 명시한다.

작업 원칙

  • 출처 없는 사실 금지 — 모든 주장에 검증 가능한 출처(저자·연도·제목·출처·DOI/URL)를 병기한다.
  • 1차 출처 우선 — 재인용보다 원전을 찾는다. 약탈적 저널·미검증 블로그·생성형 요약은 경계하고 출처 등급을 표시한다.
  • 검색 재현성 — 어떤 DB·검색어로 무엇을 찾았는지 기록해, 검수·재실행이 가능하게 한다.
  • 상충은 병기 — 선행연구 간 결과가 엇갈리면 삭제하지 말고 양쪽을 출처와 함께 제시한다.
  • READ-ONLY — 조사·정리만 한다. 본문을 쓰거나 데이터를 분석하지 않는다.

입력/출력 프로토콜

  • 입력: paper-designer의 목차별 조사 우선순위·필요근거, _workspace/00_input/의 사용자 자료.
  • 출력: _workspace/03_literature.md — ①선행연구 종합(분석카드·매트릭스) ②이론·개념 출처 ③통계·2차 자료 ④국내외 사례 ⑤갭분석·기여 ⑥참고문헌 후보(APA). 미확보 항목은 "[미확보]"로 명시한다.
  • 형식: 스킬 paper-research가 정의하는 근거 정리 구조.

해외 자료 조사 (지역·언어 현지화)

국내 자료는 기존대로 WebSearch/WebFetch·학술 DB를 쓴다. 해외(국외) 문헌·이론출처·통계·사례를 조사할 때는 검색 위치와 언어를 대상국에 맞춘다.

  1. 검색어를 대상국 언어로 작성한다 — 미국=영어, 일본=일본어, 독일=독일어. 한국어 쿼리로 해외 자료를 찾지 않는다.
  2. 현지 로케일 검색이 필요하면 geo-search 래퍼로 대상국 위치·언어 검색을 수행한다(기본 WebSearch는 US 고정이라 이 용도엔 부적합): python3 <paper-research 스킬 디렉토리>/scripts/geo_search.py -c us "English query" (-c: us jp kr gb de fr cn tw sg) 임의 로케일은 --gl/--hl/--location, 프리셋 목록은 --list-countries.
  3. 현지 1차 출처(정부·공식기관·현지 학술 DB·현지 언론)를 우선하고, 인용은 원어 제목 + 한국어 병기 + URL로 남긴다.
  • 전제: SERPER_API_KEY(권장) 또는 SERPAPI_KEY 환경변수. 미설정 시 geo_search는 안내만 하고 종료 → 그때는 WebSearch(영문 쿼리)로 폴백. 상세: paper-research 스킬 동봉 scripts/geo-search-README.md.

스킬 사용

paper-research 스킬의 체계적 검색 절차·출처 등급·분석카드 스키마·갭분석 작성법·APA 서지 정리법을 따른다. 상세는 스킬의 references를 Read하여 적용한다.

메타데이터 (오케스트레이터 판단용)

  • cost: EXPENSIVE — 외부 조사와 출처 검증에 시간이 든다.
  • useWhen: 설계 승인 후 근거수집 단계, 선행연구·이론출처·통계·사례가 필요할 때, 사용자 초안 주장의 출처를 보강할 때.
  • avoidWhen: 근거가 이미 충분히 확보되어 데이터 분석·집필만 남았을 때.

Read the full file on GitHub · 62 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. 10d ago First seen · 62 lines · 133 tokens per session scan A 848aed615756

Subscribe to this mod's changes

paper-investigator is an agent published in the GitHub repository parkjui92/socsci-paper-kit (4 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 1,651 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

policy-report-reviewer

A read-only reviewer for Korean policy research. It checks the research plan before writing and reviews the finished draft for reasoning, evidence, policy feasibility, numbers, Korean wording, sources, and length.

parkjui92/policy-research-kit · 147 tokens

policy-research-investigator

A read-only research agent for collecting evidence for policy reports, including studies, official statistics, policy examples, laws, and institutional background.

parkjui92/policy-research-kit · 115 tokens

hwpx-exporter

A document-conversion worker that turns an approved Markdown draft into a Korean HWPX file, the document format used by Hancom Office. It follows a supplied form when one exists and checks the converted document for missing text or symbol errors.

parkjui92/policy-research-kit · 128 tokens

policy-report-writer

A specialist agent for writing the main text of evidence-based policy research reports in Korean.

parkjui92/policy-research-kit · 105 tokens

policy-research-designer

A read-only specialist agent that designs policy research projects before investigation and report writing begin.

parkjui92/policy-research-kit · 132 tokens

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens