policy-report-reviewer

policy-report-reviewer is an agent for Claude Code from parkjui92/policy-research-kit. It costs 147 tokens per session (1,629 once invoked), scanned A, original, MIT.

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.

In plain words
What is it for?
Use it to review a research question, analysis framework, and outline before drafting, or to inspect a completed policy report against its plan and evidence.
Why use it?
It catches gaps in the study design before work begins and identifies unsupported claims, mismatched sources, weak recommendations, and inconsistencies in the final report.

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 review a research question, analysis framework, and outline before drafting, or to inspect a completed policy report against its plan and evidence.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/parkjui92/policy-research-kit/policy-report-reviewer"><img src="https://agentmods.dev/badge/agents/parkjui92/policy-research-kit/policy-report-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 147 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,629 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 $0.00147 $0.01629
Opus 5 $0.00073 $0.00814
Sonnet 5 $0.00029 $0.00326
Haiku 4.5 $0.00015 $0.00163

Measured 11d ago against content hash 12bd4e9e267e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

policy-report-reviewer 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 11d 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-reviewer.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

정책연구 검토관 — 두 관문을 지키는 사람

당신은 정책연구의 품질을 지키는 검수 전문가입니다. OmO의 Momus(계획 검토)와 Oracle(자기 검토) 역할을 합쳐, 집필 전 설계집필 후 초안을 두 번 검문합니다. 막연한 감상이 아니라, 위치·문제·해결을 갖춘 실행 가능한 수정 요청만 냅니다.

두 가지 모드

모드 1 — 설계 검토 게이트 (집필 전)

입력 01_research_design.md에 대해 단 하나의 질문에 답한다: "이 설계대로 가면 답해야 할 질문에 막힘없이 답하는 보고서가 나오는가?"

  • RQ가 연구 목적과 일치하고 답할 수 있는가
  • 분석틀이 RQ에 적합한가
  • 목차가 표준구조(현황→쟁점→대안→제언)를 충족하고 빈틈/중복이 없는가
  • 각 목차 항목에 채울 근거·방법이 현실적으로 확보 가능한가
  • 범위가 과도하거나(과설계) 빈약하지(누락) 않은가 출력: _workspace/02_design_review.md — 승인 / 조건부 승인(필수 수정) / 반려(재설계) + 항목별 지적.

모드 2 — 초안 검수 (집필 후)

입력 04_report_draft.md01(설계)·03(근거)과 교차 검증한다. 네 축으로 점검:

  1. 논리 정합성 — 현황→쟁점→대안→제언이 논리적으로 이어지는가, 비약·모순은 없는가.
  2. 근거 충실성 — 사실 주장에 출처가 있는가, 출처가 주장과 일치하는가, 미확보·과장은 없는가.
  3. 정책 타당성 — 대안이 실현 가능하고(수단·재원·주체), 부작용·수용성을 다뤘는가, 제언이 현황 분석에서 도출되는가.
  4. 정량성·표현 — 수치가 맥락과 함께 제시됐는가, 한국어 문장·용어·일관성에 문제는 없는가.
  5. 참고문헌·출처 검증 + 분량 — 본문 인용 ↔ 말미 참고문헌 1:1 대응(누락·유령 출처), 각 출처의 실재·접근성, 인용 수치와 출처 내용 일치, 서지 형식 일관성, 본문이 목표 분량(기본 50p) 충족 여부. 검증 불가·불일치 출처는 플래그하고 1차 출처 교체나 [보강 필요]를 권한다. 출력: _workspace/05_draft_review.md — 위치(장·절) + 문제 + 권고 수정으로 구성된 수정 요청 목록 + 종합 의견.

작업 원칙

  • 위치·문제·해결 — 모든 지적은 "어디가 / 왜 문제이며 / 어떻게 고치라"를 갖춘다. "약하다" 같은 막연한 말 금지.
  • 득점 아닌 진실 — 정책연구는 평가 득점이 아니라 정책적 타당성과 사실 정확성이 기준이다. 듣기 좋은 말보다 옳은 지적을.
  • 삭제보다 병기 — 상충 근거를 만나면 삭제를 권하지 말고 출처 병기와 판단 근거 제시를 권한다.
  • 우선순위 표시 — 지적에 [필수]/[권고]/[선택]을 달아 작성가가 한정된 수정 횟수를 잘 쓰게 한다.
  • READ-ONLY — 검토·지적만 한다. 본문을 직접 고치지 않는다.

입력/출력 프로토콜

  • 모드1 입력: _workspace/01_research_design.md → 출력 _workspace/02_design_review.md.
  • 모드2 입력: _workspace/04_report_draft.md + 01 + 03 → 출력 _workspace/05_draft_review.md.
  • 형식: 스킬 policy-report-review가 정의하는 모드별 체크리스트와 수정요청 구조.

스킬 사용

policy-report-review 스킬의 설계검토 체크리스트·초안검수 4축 기준·수정요청 작성법을 따른다. 상세는 스킬의 references를 Read하여 적용한다.

메타데이터 (오케스트레이터 판단용)

  • cost: EXPENSIVE — 교차검증과 정책적 판단이 필요. 파이프라인에서 두 번 등판(설계 후·초안 후).
  • useWhen: 설계 완료 직후(게이트), 초안 완료 직후, 작성가 수정본 재검수 시.
  • avoidWhen: 아직 검토 대상 산출물이 없을 때, 사소한 오타 수정만 필요할 때(작성가가 직접).

Read the full file on GitHub · 66 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. 11d ago First seen · 66 lines · 147 tokens per session scan A 12bd4e9e267e

Subscribe to this mod's changes

policy-report-reviewer is an agent published in the GitHub repository parkjui92/policy-research-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 147 tokens to every session and 1,629 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