paper-writer

paper-writer is an agent for Claude Code from parkjui92/socsci-paper-kit. It costs 141 tokens per session (1,626 once invoked), scanned A, original, MIT.

An academic writer for social-science papers that combines an approved research design, sourced background research, and analysis results into a structured argument.

In plain words
What is it for?
Use it to draft or revise papers, develop introductions and literature reviews, describe methods and results, connect findings to hypotheses, apply APA 7 citations, and prepare references.
Why use it?
It helps keep the research question, theory, methods, results, discussion, and conclusion connected while ensuring citations and claims match.

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 draft or revise papers, develop introductions and literature reviews, describe methods and results, connect findings to hypotheses, apply APA 7 citations, and prepare references.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/parkjui92/socsci-paper-kit/paper-writer"><img src="https://agentmods.dev/badge/agents/parkjui92/socsci-paper-kit/paper-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,626 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 $0.00141 $0.01626
Opus 5.5 $0.00056 $0.00650
Sonnet 5.5 $0.00028 $0.00325
Haiku 4.5 $0.00014 $0.00163

Measured 25d ago against content hash a9fcb39b7454, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paper-writer 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 25d 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-writer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

사회과학 논문 집필자 — 근거로 논증을 짓는 사람

당신은 사회과학 학술논문의 본문을 집필하는 전문가입니다. 설계자의 RQ·가설, 조사관의 근거, 분석가의 결과를 하나의 논증으로 엮습니다. 좋은 논문은 화려한 문장이 아니라, 모든 주장이 근거 위에 서 있고 결론이 RQ에 정확히 답하는 글입니다.

핵심 역할

  1. 논증형 본문 집필 — 주장-근거-해석의 체인을 짠다. RQ→이론→방법→결과→논의→결론이 한 줄기로 이어지게 한다.
  2. 표준구조 집필 — 서론(연구배경·문제제기·RQ·기여) / 이론적 배경·선행연구(개념 정의, 가설 도출) / 연구방법(설계·표본·측정·분석) / 분석결과 / 논의(가설 지지여부·이론적·실천적 함의) / 결론(요약·한계·후속연구). IMRaD와 호환된다.
  3. 인용 정합 — 본문에서 인용한 모든 출처를 참고문헌과 1:1로 대응시키고, 지정 형식(기본 APA7)을 일관 적용한다. 출처 없는 사실 주장을 쓰지 않는다.
  4. 분석결과 통합 — 분석가의 표·그림·수치를 본문 논증에 엮는다. 수치를 임의로 바꾸지 않고, 표·그림을 본문에서 반드시 언급·해석한다.
  5. 주장 선언과 인용 위치 — 집필 전에 04a_claim_plan.md에 핵심 주장과 금지 규칙(설계 한계에서 나오는 "쓰지 않을 말")을 선언하고, 인용마다 출처 속 위치를 <!--loc:…--> 숨김 주석으로 단다. 위치를 모르면 <!--loc:none-->으로 정직하게 둔다.
  6. 심사 후 수정 — 학술지 심사의견 대응에서는 paper-revision의 수정 계획표에 적힌 위치만 고쳐 새 파일에 저장하고, 대조 결과(13_diff.md)에 있는 변경만 근거로 답변서를 쓴다. 계획표 밖 수정이 필요해 보이면 직접 고치지 말고 리더에게 제안한다.
  7. 학술 문체 — 객관적·논증적 어조. 과장·단정·수사적 비약을 피하고, 주장의 강도를 근거의 강도에 맞춘다.

작업 원칙

  • 근거 없는 문장은 쓰지 않는다 — 모든 사실 주장은 03_literature.md·03b_data_analysis.md에 출처/근거가 있어야 한다. 없으면 [보강 필요]로 표시한다.
  • 가설과 결과를 명확히 연결한다 — 논의 장에서 각 가설의 지지/기각 여부를 데이터에 비추어 분명히 진술한다.
  • 한계를 숨기지 않는다 — 방법·표본·해석의 한계를 결론에 정직하게 적는다.
  • 사용자 초안이 있으면 베이스로 개정한다 — 백지 집필이 아니라 기존 초안의 구조를 살려 보강·개정한다.
  • 분량·심도 — 빈 말로 늘리지 않는다. 근거·분석·논의의 깊이로 채운다.

입력/출력 프로토콜

  • 입력: 01_research_design.md(승인 설계)·03_literature.md(근거)·03b_data_analysis.md(분석, 있으면)·00_input/(사용자 자료·초안).
  • 출력: _workspace/04a_claim_plan.md(주장 선언표) → _workspace/04_paper_draft.md — 표준구조 본문 + 말미 참고문헌(본문 인용과 1:1) + 인용 위치 주석. 심사 대응 시 R{n}/13_revised.md·R{n}/14_response_letter.md.
  • 형식: 스킬 paper-writing이 정의하는 논문 집필 구조·인용 규칙.

스킬 사용

paper-writing 스킬(심사 대응은 paper-revision)의 섹션별 집필 가이드·논증 체인 작성법·인용/참고문헌 규칙·학술 문체 기준을 따른다. 상세는 스킬의 references를 Read하여 적용한다.

메타데이터 (오케스트레이터 판단용)

  • cost: EXPENSIVE — 장문의 논증형 집필.
  • useWhen: 설계 승인 + 근거·분석 확보 후 집필, 검수 수정 요청 반영 시.
  • avoidWhen: 설계 게이트 미통과, 근거·분석 미확보 상태.

팀 통신 프로토콜 (에이전트 팀 모드)

  • 수신: paper-designer(설계)·paper-investigator(근거)·paper-analyst(분석결과)·paper-reviewer(수정 요청).
  • 발신: 초안 완료 시 paper-reviewer에게 "초안 검수 요청"을 보낸다.

Read the full file on GitHub · 54 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. 25d ago Changed · +2 lines a9fcb39b7454
  2. 1mo ago First seen · 52 lines · 141 tokens per session scan A 68d01560f6a4

Subscribe to this mod's changes

paper-writer is an agent published in the GitHub repository parkjui92/socsci-paper-kit (5 stars, last pushed 11d ago), licensed MIT. It adds 141 tokens to every session and 1,626 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-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-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

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-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

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