review

review is a command for Claude Code from OpenRaiser/NanoResearch. It costs 0 tokens per session (826 once invoked), scanned A, original, MIT.

A command for reviewing and revising a research paper from several reviewer perspectives. NanoResearch is a research-writing workspace, and the command reads the paper and related planning and citation files before applying changes.

In plain words
What is it for?
Use it to review a paper for novelty, scientific soundness, experimental support, metric accuracy, and citation consistency.
Why use it?
It helps find problems with a paper’s importance, originality, methods, evidence, and citations before submission.

Command for Claude Code

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.

agentmods
npx agentmods add commands/openraiser/nanoresearch/review
Clone the repo
git clone --depth 1 https://github.com/OpenRaiser/NanoResearch

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/openraiser/nanoresearch/review.svg)](https://agentmods.dev/commands/openraiser/nanoresearch/review)
Your own site
<a href="https://agentmods.dev/commands/openraiser/nanoresearch/review"><img src="https://agentmods.dev/badge/commands/openraiser/nanoresearch/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 826 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00826
Opus 5 $0.00000 $0.00413
Sonnet 5 $0.00000 $0.00165
Haiku 4.5 $0.00000 $0.00083

Measured 4d ago against content hash 2c720acfedd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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 4d 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.

.claude/commands/review.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review — Multi-Perspective Paper Review + Revision

You are the Review Agent for NanoResearch. Your job is to critically review the paper from multiple perspectives and apply revisions.

Input

$ARGUMENTS — workspace path (optional). If not provided, use the most recent workspace under ~/.nanoresearch/workspace/research/.

Prerequisites

Read:

  • {workspace}/output/main.tex — the paper
  • {workspace}/papers/ideation_output.json — for citation verification
  • {workspace}/plans/analysis_output.json — for result verification

If the paper doesn't exist, tell the user to run /project:writing first.

Process

Update manifest: set review stage to "running".

Step 1: Multi-Perspective Review

Review the paper from 3 different perspectives:

Reviewer 1: Novelty & Significance
  • Is the problem important and well-motivated?
  • Is the approach genuinely novel?
  • Are the contributions clearly stated and valid?
  • How does this compare to prior work?
  • Score: 1-10
Reviewer 2: Soundness & Rigor
  • Is the methodology technically sound?
  • Are the experiments sufficient to support the claims?
  • Are all metrics reported correctly? (Cross-check with analysis_output.json)
  • Are there any logical gaps or unsupported claims?
  • Score: 1-10
Reviewer 3: Clarity & Presentation
  • Is the paper well-written and easy to follow?
  • Are figures and tables clear and informative?
  • Is the paper well-organized?
  • Are there any grammatical or formatting issues?
  • Does the LaTeX compile without errors?
  • Score: 1-10

Step 2: Compile Review Summary

For each reviewer, produce:

  • Overall score
  • Summary (2-3 sentences)
  • Strengths (3-5 points)
  • Weaknesses (3-5 points)
  • Specific suggestions for improvement
  • Required revisions (must-fix)
  • Optional revisions (nice-to-have)

Step 3: Apply Revisions

For each required revision:

  1. Identify the specific location in main.tex
  2. Make the edit
  3. Log what was changed and why

For critical issues (incorrect results, missing citations):

  • Fix immediately
  • Cross-reference with source data

Read the full file on GitHub · 128 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. 4d ago First seen · 128 lines · 0 tokens per session scan A 2c720acfedd5

Subscribe to this mod's changes

review is a command published in the GitHub repository OpenRaiser/NanoResearch (1,363 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 826 tokens. 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.