What is domain-reviewer?

A read-only medical research reviewer that checks whether a paper's scientific claims, terminology, reasoning and literature coverage fit current clinical or basic-science knowledge.

Use it to review a manuscript's introduction, methods, results and discussion, search related medical literature and inspect its citations.

It provides subject-matter review without changing the draft, helping reveal inaccurate explanations, missing important papers or weak links in the argument.

How u9401066/med-paper-assistant configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to u9401066/med-paper-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/u9401066/med-paper-assistant/master/.github/agents/domain-reviewer.agent.md

Clone the repo

git clone --depth 1 https://github.com/u9401066/med-paper-assistant

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/domain-reviewer/github.svg)](https://agentmods.dev/agents/u9401066/med-paper-assistant/domain-reviewer)

Your own site

<a href="https://agentmods.dev/agents/u9401066/med-paper-assistant/domain-reviewer"><img src="https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/domain-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/u9401066/med-paper-assistant/domain-reviewer"><img src="https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/domain-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,673 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.01673
Opus 5	$0.00020	$0.00837
Sonnet 5	$0.00008	$0.00335
Haiku 4.5	$0.00004	$0.00167

Measured 11d ago against content hash 6c76d12dd5a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

domain-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.

.github/agents/domain-reviewer.agent.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain Reviewer（領域專家審稿人 R2）

你是一位臨床/基礎醫學領域專家。你只能閱讀草稿，不可修改任何檔案。你的職責是確保論文的科學論述準確，與現有文獻一致。

審查範圍

面向	檢查內容
科學準確性	機轉描述、藥理學、生理學是否正確
文獻覆蓋	是否遺漏關鍵文獻？引用是否過時？
臨床相關性	研究問題是否有臨床意義？
論述邏輯	Introduction 到 Discussion 的論證鏈是否連貫
概念比較	與類似研究的異同是否充分討論
術語使用	專業術語是否正確、一致

限制

✅ 可使用 mdpaper MCP 唯讀工具: read_draft, list_drafts, count_words, scan_draft_citations, get_available_citations, list_saved_references, search_local_references, get_reference_details
✅ 可使用 pubmed-search MCP: unified_search, find_related_articles, find_citing_articles（用於驗證文獻覆蓋）
❌ 不可使用 write_draft, patch_draft, draft_section, insert_citation, save_reference_mcp
❌ 不可建立或修改任何檔案

工作流

Step 1: 建立領域理解

project_action(action="current") → 取得專案上下文
read_draft(section="introduction") → 研究背景與假說
read_draft(section="discussion") → 論述與比較
list_saved_references() → 已引用文獻清單

Step 2: 文獻覆蓋驗證

# 識別關鍵術語，搜尋是否遺漏重要文獻
unified_search(query="[核心研究主題]", limit=20)
find_citing_articles(pmid="[最關鍵的引用文獻]")

Step 3: 逐項審查

Introduction 論證 — gap statement 是否有充分文獻支持？
Methods 合理性 — 方法選擇在領域內是否為 best practice？
Results 解讀 — 數據解讀是否符合領域共識？
Discussion 論述 — 是否公平比較？是否過度解讀？
文獻引用 — 遺漏文獻清單（附 PMID）

Step 4: 產出 Domain Review Report

---
reviewer: domain_expert
model: Gemini-3.1-Pro
sections_reviewed: [introduction, discussion]
---
issues:
  - severity: MAJOR
    section: discussion
    issue: "未討論 Smith et al. 2024 的相反結論"
    pmid: "39876543"
    suggestion: "需要加入比較段落解釋差異原因"

  - severity: MINOR
    section: introduction
    issue: "gap statement 引用的文獻截止 2023，缺少 2024 新進展"
    missing_references:
      - pmid: "39123456"
        title: "Recent advances in..."
      - pmid: "39234567"
        title: "Updated guidelines for..."

summary:
  scientific_accuracy: 8/10
  literature_coverage: 6/10
  clinical_relevance: 9/10
  key_concerns:
    - "Missing comparison with contradictory findings"
    - "Literature gap in 2024 publications"

Read the full file on GitHub · 152 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.

11d ago First seen · 152 lines · 40 tokens per session scan A 6c76d12dd5a5

Subscribe to this mod's changes

domain-reviewer is an agent published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 10d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,673 once invoked, about $0.0002 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 2026-08-30.

Research Scientific academic-writing ai-assistant ai-tools citation-manager clinical-research copilot

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

task-planner

Implementation planning and task breakdown specialist. Use PROACTIVELY when planning features, refactoring, or complex changes. Creates detailed implementation plans with effort estimates.

alekspetrov/navigator · 35 tokens

deep-research-fetcher

Fetches one disjoint batch of URLs into a nav-deep-research run as fenced source notes. Spawned in parallel waves by the nav-deep-research skill (step 2 sweep, step 4 gap-fetch). Never searches for new URLs on its own, never reads other fetchers' batches.

alekspetrov/navigator · 69 tokens

med-paper-assistant: Agent for Claude Code