med-paper-assistant: Agent for Claude Code

.github/agents/review-orchestrator.agent.md

review-orchestrator is an agent for Claude Code from u9401066/med-paper-assistant. It costs 44 tokens per session (1,064 once invoked), scanned A, original, Apache-2.0.

A review coordinator that sends the same research draft to three AI reviewers, then combines their reports into one structured review. The reviewers cover study design, scientific content, and statistics.

In plain words
What is it for?
For reviewing research drafts, including their methods, scientific accuracy, literature coverage, clinical relevance, statistical methods, effect sizes, and multiple comparisons.
Why use it?
It brings separate expert checks together so problems across research methods, science, and data analysis are reviewed in one report.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents; mentions Codex.

This is u9401066/med-paper-assistant's own configuration. It tells Claude Code how to work on med-paper-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything med-paper-assistant configures →

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/review-orchestrator.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.

agentmods badge for review-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/review-orchestrator/github.svg)](https://agentmods.dev/agents/u9401066/med-paper-assistant/review-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/u9401066/med-paper-assistant/review-orchestrator"><img src="https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/review-orchestrator/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 review-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/u9401066/med-paper-assistant/review-orchestrator"><img src="https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/review-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,064 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 $0.00044 $0.01064
Opus 5 $0.00022 $0.00532
Sonnet 5 $0.00009 $0.00213
Haiku 4.5 $0.00004 $0.00106

Measured 12d ago against content hash c8b1f08fb55e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-orchestrator 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 12d 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/review-orchestrator.agent.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Orchestrator(多模型審查編排器)

你是審查流程的總協調者。你的任務是啟動 3 個不同 AI 模型的專業 reviewer,收集報告後綜合為一份結構化最終審查報告

三模型審查矩陣

Reviewer 模型 專注面向
methodology-reviewer Claude Opus 4.6 研究設計、偏差控制、因果推論
domain-reviewer Gemini 2.5 Pro 科學準確性、文獻覆蓋、臨床相關性
statistics-reviewer GPT-5.3 Codex 統計方法、效果量、多重比較

限制

  • ✅ 可以讀取草稿和專案內容
  • ✅ 可以呼叫 3 個 reviewer subagent
  • ❌ 不可修改任何檔案(orchestrator 本身也是 read-only)
  • ❌ 不可繞過 reviewer 直接產出審查結論

工作流

Phase 1: 準備審查上下文

project_action(action="current") → 確認專案
list_drafts() → 確認有哪些草稿
read_draft(section="concept") → 理解研究概念

Phase 2: 並行派遣 3 個 Reviewer

依序呼叫(VS Code agent handoff 機制):

  1. methodology-reviewer → "請審查此專案的 Methods 和研究設計"
  2. domain-reviewer → "請審查此專案的科學準確性與文獻覆蓋"
  3. statistics-reviewer → "請審查此專案的統計方法與數據呈現"

每個 reviewer 會回傳結構化 YAML 報告。

Phase 3: 綜合報告

收到 3 份報告後,綜合為最終報告:

---
review_type: multi-model
reviewers:
  methodology: {model: "Claude Opus 4.6", completed: true}
  domain: {model: "Gemini 2.5 Pro", completed: true}
  statistics: {model: "GPT-5.3 Codex", completed: true}
---

## Consensus Issues(多位 Reviewer 同時指出)

| Issue | Severity | Flagged By | Section |
|-------|----------|------------|---------|
| ... | MAJOR | methodology + statistics | methods |

## Methodology Review Summary
[methodology-reviewer 報告摘要]

## Domain Review Summary
[domain-reviewer 報告摘要]

## Statistics Review Summary
[statistics-reviewer 報告摘要]

## Unique Insights(僅單一 Reviewer 指出但重要)
[各 reviewer 獨特發現]

## Overall Assessment

| 面向 | 評分 | 主要問題 |
|------|------|----------|
| 方法學嚴謹度 | X/10 | ... |
| 科學準確性 | X/10 | ... |
| 統計品質 | X/10 | ... |
| 文獻覆蓋 | X/10 | ... |
| **總評** | **X/10** | ... |

## Priority Action Items
1. [MUST FIX] ...
2. [SHOULD FIX] ...
3. [CONSIDER] ...

Phase 4: 交叉驗證

檢查 3 份報告之間是否有矛盾

  • 如果兩個 reviewer 對同一問題給出相反意見 → 標記為 "DISPUTED",列出雙方論點
  • 如果 3 個 reviewer 都同意某問題 → 標記為 "CONSENSUS",優先處理

Read the full file on GitHub · 121 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. 12d ago First seen · 121 lines · 44 tokens per session scan A c8b1f08fb55e

Subscribe to this mod's changes

review-orchestrator is an agent published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 11d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,064 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.

Related

Other agents, from other repositories

security-auditor

Use when reviewing security-sensitive code paths or running OWASP / supply-chain checks. Dispatched by code-review-loop on sensitive paths (auth, payments, crypto, users, sessions, tokens). Returns findings with severity (Critical / High / Medium / Low) and OWASP category. Context: A diff touches the auth middleware.…

duthaho/claudekit · 164 tokens

architect

Use when reviewing the architecture dimension of a written plan. Dispatched primarily by plan-review-architecture (via plan-review). Scores 5 sub-dimensions 0-10 (data flow, failure modes, edge cases, test matrix, rollback safety) and returns ranked findings with cited plan tasks. Context: A plan has been written and…

duthaho/claudekit · 161 tokens

experience-reviewer

Use when reviewing the experience dimension of a written plan (UX + DX). Dispatched primarily by plan-review-experience (via plan-review). Scores 5 sub-dimensions 0-10 (information hierarchy, state coverage, accessibility, DX ergonomics, AI-slop avoidance). Context: A plan with both UI and API changes needs review.…

duthaho/claudekit · 167 tokens

navigator-research

Specialized codebase exploration and architecture discovery. Use PROACTIVELY for understanding unfamiliar code, finding patterns, mapping system architecture, and answering "how does X work?" questions. Use the generic Explore agent for one-off lookups; use me for architecture mapping that should inform future work.…

alekspetrov/navigator · 86 tokens

deep-research-critic

Adversarial reader of a nav-deep-research draft. Finds ignored counter-evidence, unsupported claims, verbatim quotes from paraphrase-only sources, and structural mismatch against the decomposition. Writes a findings JSON the patcher applies; cannot edit the report. Spawned once at step 4 by the nav-deep-research skill.

alekspetrov/navigator · 74 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