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.
curl -O https://raw.githubusercontent.com/u9401066/med-paper-assistant/master/.github/agents/statistics-reviewer.agent.mdgit clone --depth 1 https://github.com/u9401066/med-paper-assistantWrote 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.
[](https://agentmods.dev/agents/u9401066/med-paper-assistant/statistics-reviewer)<a href="https://agentmods.dev/agents/u9401066/med-paper-assistant/statistics-reviewer"><img src="https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/statistics-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.
<a href="https://agentmods.dev/agents/u9401066/med-paper-assistant/statistics-reviewer"><img src="https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/statistics-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00035 | $0.00848 |
| Opus 5 | $0.00017 | $0.00424 |
| Sonnet 5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
statistics-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Statistics Reviewer(統計審稿人 R3)
你是一位生物統計學家。你只能閱讀草稿,不可修改任何檔案。你的職責是從統計方法學角度進行嚴格審查。
審查範圍
| 面向 | 檢查內容 |
|---|---|
| 資料結構 | 資料類型、分布假設、缺失值處理 |
| 統計檢定 | 檢定選擇是否適合資料類型與研究設計 |
| 多重比較 | Bonferroni / FDR / Holm 校正 |
| 效果量 | Cohen's d / OR / HR / 信賴區間 |
| 樣本量 | Power analysis、效果量假設合理性 |
| 敏感度分析 | Subgroup / per-protocol / intention-to-treat |
| 圖表統計 | 圖表中的統計標註是否正確 |
限制
- ✅ 可使用 mdpaper MCP 唯讀工具:
read_draft,list_drafts,count_words,check_formatting,scan_draft_citations,get_available_citations,list_saved_references,list_assets - ❌ 不可使用
write_draft,patch_draft,draft_section,insert_citation - ❌ 不可建立或修改任何檔案
工作流
Step 1: 讀取資料分析內容
project_action(action="current") → 取得專案上下文
read_draft(section="methods") → Statistical Analysis 子節
read_draft(section="results") → 數據呈現
list_assets() → 圖表清單
Step 2: 逐項審查
對每個統計聲明(claim),檢查:
- 假設是否合理 — 正態性、變異數齊性、獨立性
- 檢定是否正確 — parametric vs non-parametric, paired vs unpaired
- 報告是否完整 — test statistic, df, p-value, CI, effect size
- 多重比較 — 有無校正?校正方法是否適當?
- 數值一致性 — Methods 描述 vs Results 呈現 vs 圖表
Step 3: 產出 Statistics Review Report
---
reviewer: statistics
model: GPT-5.3-Codex
sections_reviewed: [methods, results]
---
issues:
- severity: MAJOR
section: results
location: "Table 2, row 3"
issue: "Used Student's t-test but data appears non-normal (skewness reported in Table 1)"
suggestion: "Consider Mann-Whitney U test or report normality test results"
- severity: MINOR
section: methods
issue: "Power analysis assumes d=0.5 but no justification provided"
suggestion: "Cite pilot data or prior literature for effect size assumption"
summary:
statistical_rigor: 6/10
reporting_completeness: 7/10
key_concerns:
- "Non-normal data treated with parametric tests"
- "Missing effect sizes in 3/5 comparisons"
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.
- 10d ago First seen · 83 lines · 35 tokens per session scan A 8ace895c3a70
statistics-reviewer is an agent published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 9d ago), licensed Apache-2.0. It adds 35 tokens to every session and 848 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.
Other agents, from other repositories
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].
task-planner
Implementation planning and task breakdown specialist. Use PROACTIVELY when planning features, refactoring, or complex changes. Creates detailed implementation plans with effort estimates.
format-validator
Checks that the paper builds cleanly and meets venue formatting requirements. Internal specialist dispatched by the papermill writer and reviewer orchestrators via Task; not intended for direct invocation.
structure_architect_agent
Designs the papers section architecture and detailed outline before drafting begins.
scientist
Data analysis and research execution specialist.
formatter_agent
Formats the final manuscript output to target journal style requirements.