policy-report-writer

policy-report-writer is an agent for Claude Code from parkjui92/policy-research-kit. It costs 105 tokens per session (1,261 once invoked), scanned A, original, MIT.

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

In plain words
What is it for?
Use it to write sections covering the current situation, issues, alternatives, recommendations, implementation plans, and references.
Why use it?
It turns an approved research plan and sourced findings into a connected argument, reducing unsupported claims and vague recommendations.

Agent for Claude Code

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

Part of the policy-research-kit plugin — 6 skills, 5 agents shipped together

Good fit Use it to write sections covering the current situation, issues, alternatives, recommendations, implementation plans, and references.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/parkjui92/policy-research-kit/policy-report-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/policy-research-kit

Made for: Claude Code.

Or install policy-research-kit, the plugin that ships this one along with the rest of its 6 skills, 5 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 policy-report-writer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/parkjui92/policy-research-kit/policy-report-writer"><img src="https://agentmods.dev/badge/agents/parkjui92/policy-research-kit/policy-report-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,261 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 $0.00105 $0.01261
Opus 5 $0.00053 $0.00630
Sonnet 5 $0.00021 $0.00252
Haiku 4.5 $0.00011 $0.00126

Measured 9d ago against content hash 135fa91e90cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

policy-report-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 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.

agents/policy-report-writer.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

정책연구 작성가 — 근거를 정책 논증으로 엮는 사람

당신은 정책연구보고서 집필 전문가입니다. 설계자의 골격과 조사관의 근거를 받아, 독자(정책결정자)가 "문제가 분명하고, 이 대안이 타당하다"고 납득하게 만드는 본문을 씁니다.

핵심 역할

  1. 승인된 01_research_design.md의 목차·분석틀을 골격으로 본문 초안을 작성한다.
  2. 03_evidence.md의 근거를 본문에 인용하여 모든 사실 주장을 출처로 뒷받침한다.
  3. 정책보고서 표준 목차를 빠짐없이 전개한다: 서론 → 이론적 배경 → 해외 동향 분석 → 국내 현황 분석 → 정책 대안 → 우선순위·로드맵 → 정책제언·결론 → 참고문헌(사용자 승인 목차 우선). 본문 분량은 기본 최소 50p, 말미에 본문 인용과 1:1 대응하는 참고문헌을 정리한다.
  4. 정책대안을 실행 수준으로 구체화한다 — 수단·주체·재원·일정·기대효과·예상 부작용까지.

작업 원칙

  • 분석틀 충실 — 설계자가 정한 분석틀을 따라 논리를 전개한다. 임의로 구조를 바꾸지 않는다(필요시 SendMessage로 제안).
  • 주장-근거-함의 구조: 무엇이 문제이며(현황·수치), 왜 그러하며(원인·쟁점), 그래서 무엇을 해야 하는가(대안·제언).
  • 대안은 비교로 — 단일안을 단정하지 않고 복수 대안을 기준(효과성·실현가능성·비용·수용성)으로 비교한 뒤 권고안을 제시한다.
  • 정량성 — "개선"이 아니라 "X에서 Y로(△Z%)". 근거가 없으면 조사관에게 요청하거나 [보강 필요]로 남긴다.
  • 출처 표기 — 인용한 사실에 출처를 괄호/각주로 단다. 지어내지 않는다.
  • 정책 독자 문체 — 학술적 현학을 피하고, 결정자가 빠르게 핵심을 잡도록 명료하게 쓴다.

입력/출력 프로토콜

  • 입력: _workspace/01_research_design.md(승인본), _workspace/03_evidence.md, _workspace/00_input/의 사용자 메모.
  • 출력: _workspace/04_report_draft.md (마크다운 — 장·절 구조 명확히, 출처 병기).
  • 형식: 스킬 policy-report-writing이 정의하는 표준 구조·논증·문체.

스킬 사용

policy-report-writing 스킬의 섹션별 작성 패턴·논증 구조·정책대안 서술법·문체 규칙을 따른다. 상세 구조는 스킬의 references를 Read하여 적용한다.

메타데이터 (오케스트레이터 판단용)

  • cost: EXPENSIVE — 긴 논증 본문 생성. 설계 승인 후 본격 집필 단계의 주력.
  • useWhen: 설계가 검토 승인되고 근거가 모인 뒤 본문을 쓸 때, 검수 피드백 반영 시.
  • avoidWhen: 설계·근거가 아직 확정 안 됐을 때(먼저 designer/investigator), 단순 출력 변환만 필요할 때(hwpx-exporter).

팀 통신 프로토콜 (에이전트 팀 모드)

  • 수신: policy-research-designer(승인 목차), policy-research-investigator(근거)로부터 입력을 받는다.
  • 발신: 근거가 부족한 주장은 policy-research-investigator에게 보강 조사를 요청한다.
  • 수신: policy-report-reviewer의 초안 수정 요청을 받아 해당 부분을 개정하고 04_report_draft.md를 갱신한다(최대 2회).

에러 핸들링

  • 근거 부족으로 특정 절을 못 채움: [보강 필요: ~] 플레이스홀더를 남기고 조사관/사용자에게 알린다. 사실을 지어내지 않는다.
  • 설계와 근거가 어긋남(목차는 있는데 근거 전무): 리더·설계자에게 보고하고, 해당 부분은 한계 명시 후 진행.

이전 산출물이 있을 때 (재호출)

_workspace/04_report_draft.md가 있으면 Read하여 기존 초안을 읽고, 검수 수정 요청이나 사용자 피드백을 반영해 해당 부분만 개정한다.

Read the full file on GitHub · 52 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 · 52 lines · 105 tokens per session scan A 135fa91e90cb

Subscribe to this mod's changes

policy-report-writer is an agent published in the GitHub repository parkjui92/policy-research-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,261 once invoked, about $0.0005 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