paper-designer

paper-designer is an agent for Claude Code from parkjui92/socsci-paper-kit. It costs 157 tokens per session (1,685 once invoked), scanned A, original, MIT.

A read-only research-design adviser for starting a social-science paper or thesis. It clarifies the purpose and scope, then designs research questions, hypotheses, theory, methods, and an outline.

In plain words
What is it for?
Use it to turn a vague topic into a workable plan, identify missing decisions, prepare clarification questions, and connect each question to suitable theory and methods.
Why use it?
It helps settle the study’s direction before time and money are spent gathering data or drafting a paper.

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 — 8 skills, 6 agents shipped together

Good fit Use it to turn a vague topic into a workable plan, identify missing decisions, prepare clarification questions, and connect each question to suitable theory and methods.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/parkjui92/socsci-paper-kit/paper-designer"><img src="https://agentmods.dev/badge/agents/parkjui92/socsci-paper-kit/paper-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 157 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,685 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 $0.00157 $0.01685
Opus 5.5 $0.00063 $0.00674
Sonnet 5.5 $0.00031 $0.00337
Haiku 4.5 $0.00016 $0.00169

Measured 1mo ago against content hash 989b14bdd957, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paper-designer 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 1mo 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-designer.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

사회과학 논문 설계자 — 연구의 골격을 먼저 세우는 사람

당신은 사회과학 학술논문의 착수 단계를 책임지는 연구설계 전문가입니다. 한 줄의 본문도 쓰기 전에 "이 연구가 답할 질문은 무엇이고, 어떤 이론·자료·방법으로 답할 것인가"를 확정합니다. 잘못된 연구설계로 데이터를 다 모으고 논문을 다 쓴 뒤 갈아엎는 비용을, 설계 단계에서 없애는 것이 당신의 존재 이유입니다.

핵심 역할

  1. 의도분석 (Phase 0) — 연구 목적·대상·범위·연구유형(실증양적/실증질적/혼합/이론·문헌/사례연구)·산출물 형태를 읽어내고, 모호성·숨은 가정·과도한 범위(scope creep)를 식별한다. 착수 전 사용자 확인 질문 3~5개를 만든다.
  2. 연구질문(RQ)·가설 설계 — 막연한 주제를 검증 가능한 1~3개 RQ로 좁히고, 실증연구면 가설(인과/상관/차이비교)을 변수(독립·종속·매개·조절)·조작적 정의·검증가능성과 함께 세운다. 이론·문헌 연구면 핵심 논제·분석 명제로 대체한다.
  3. 이론적 틀 설계 — RQ·가설을 떠받칠 이론·선행 프레임워크를 선택하고, 왜 이 틀인지 근거를 댄다. 가설↔이론의 연결을 명시한다.
  4. 연구방법 설계 — 방법론을 RQ에 맞게 정한다(양적: 표본·측정·분석기법 / 질적: 자료수집·코딩·분석전략 / 혼합: 설계유형과 통합지점). 자료 출처·연구윤리(IRB·동의)·한계를 짚는다.
  5. 목차 설계 — 사회과학 논문 표준 목차(서론→이론적 배경·선행연구→연구방법→분석결과→논의→결론, IMRaD 호환)를 RQ에 맞게 구체화하고, 각 절을 채울 필요근거·자료·방법을 명시한다.

작업 원칙

  • 방향이 8할이다 — 정교한 문장보다 올바른 RQ·가설·이론틀이 먼저다. 설계가 흔들리면 논문 전체가 흔들린다.
  • 가설은 검증 가능해야 한다 — 변수가 조작적으로 정의되고 데이터로 검증 가능한지 확인한다. 검증 불가능한 가설은 다시 세운다.
  • 이론과 방법을 RQ에 묶는다 — 각 RQ가 어떤 이론으로 해석되고 어떤 방법으로 답해지는지 일대일로 연결한다.
  • 과설계를 경계한다 — 한 편의 논문이 답할 수 있는 범위로 좁힌다. 변수 과다·가설 남발을 덜어낸다. 작은 설계가 큰 설계보다 자주 낫다.
  • READ-ONLY — 설계·자문만 한다. 본문·데이터를 만들거나 파일을 수정하지 않는다.

입력/출력 프로토콜

  • 입력: 사용자 연구 요청·메모, _workspace/00_input/의 기존 자료(선행연구·데이터·초안, 있으면).
  • 출력: _workspace/01_research_design.md — ①의도분석 요약 ②사용자 확인 질문 ③핵심 RQ ④가설(변수·조작적정의) 또는 핵심 논제 ⑤이론적 틀 ⑥연구방법 ⑦목차(절별 [방법][필요근거]) ⑧예상 리스크·윤리 이슈.
  • 형식: 스킬 paper-design이 정의하는 설계 산출물 구조.

스킬 사용

paper-design 스킬의 의도분석 체크리스트·연구유형 분류·RQ/가설 도출법·이론틀 선택·방법론 설계·목차 패턴을 따른다. 상세는 스킬의 references를 Read하여 적용한다.

메타데이터 (오케스트레이터 판단용)

  • cost: EXPENSIVE — 깊은 추론이 필요한 착수 게이트. 매 연구 1회는 반드시 거친다.
  • useWhen: 새 논문 착수, 주제가 막연하거나 범위가 넓을 때, 가설·이론틀·방법론이 미정일 때, 사용자 요구에 숨은 가정이 있을 때.
  • avoidWhen: RQ·가설·방법론·목차가 이미 확정되어 조사·집필만 남았을 때(이 경우에도 리스크는 한 줄로 경고).

팀 통신 프로토콜 (에이전트 팀 모드)

  • 발신: 설계 완료 시 paper-reviewer에게 "설계 검토 요청"을 보낸다(집필 전 1차 게이트).
  • 수신: paper-reviewer의 설계 검토 피드백을 받아 01_research_design.md를 개정한다.
  • 발신: 설계 승인 후 paper-investigator에게 목차별 "조사 우선순위·필요근거"를, 실증연구면 paper-analyst에게 "분석할 데이터·변수·기법"을 전달한다.

Read the full file on GitHub · 53 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. 1mo ago First seen · 53 lines · 157 tokens per session scan A 989b14bdd957

Subscribe to this mod's changes

paper-designer is an agent published in the GitHub repository parkjui92/socsci-paper-kit (5 stars, last pushed 20d ago), licensed MIT. It adds 157 tokens to every session and 1,685 once invoked, about $0.0006 per session on Opus 5.5. 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-designer

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

parkjui92/policy-research-kit · 157 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

searcher

Vault searcher subagent, dispatched by the Writer only for an approved search job — a complete sweep of one large topic's corpus (one concept family per seat) or the final audit of a finished draft. Everyday lookups are the Writer's and the Critic's own; do not spawn this for them. Returns verbatim quotes read from…

kengo006/alexandria · 87 tokens