review-paper

review-paper is a command for Claude Code from TobiasBlask/open-paper-machine. It costs 79 tokens per session (463 once invoked), scanned A, original, MIT.

A simulated double-blind peer review that produces two independent reports on a research paper. Peer review is the process where experts evaluate a paper before publication; double-blind means the reviewers and authors are kept anonymous to each other.

In plain words
What is it for?
Use it to review the latest draft or a specified manuscript, calibrate feedback for a venue, and create a revision checklist.
Why use it?
It gives separate feedback on research methods, contribution, theory, writing, and relevance before submitting to a conference or journal.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the open-academic-paper-machine plugin — 33 skills, 21 commands, 4 agents shipped together

Good fit Use it to review the latest draft or a specified manuscript, calibrate feedback for a venue, and create a revision checklist.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/tobiasblask/open-paper-machine/review-paper
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/TobiasBlask/open-paper-machine

Made for: Claude Code.

Or install open-academic-paper-machine, the plugin that ships this one along with the rest of its 33 skills, 21 commands, 4 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 review-paper

README.md
[![agentmods](https://agentmods.dev/badge/commands/tobiasblask/open-paper-machine/review-paper/github.svg)](https://agentmods.dev/commands/tobiasblask/open-paper-machine/review-paper)
Your own site
<a href="https://agentmods.dev/commands/tobiasblask/open-paper-machine/review-paper"><img src="https://agentmods.dev/badge/commands/tobiasblask/open-paper-machine/review-paper/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-paper

Your own site · 80×15
<a href="https://agentmods.dev/commands/tobiasblask/open-paper-machine/review-paper"><img src="https://agentmods.dev/badge/commands/tobiasblask/open-paper-machine/review-paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 463 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 $0.00079 $0.00463
Opus 5 $0.00039 $0.00231
Sonnet 5 $0.00016 $0.00093
Haiku 4.5 $0.00008 $0.00046

Measured 10d ago against content hash e56a13ec4c9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-paper 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.

commands/review-paper.md · 37 lines

What it actually says

Review Paper: $ARGUMENTS

Activate the peer-review-engine skill. Read skills/peer-review-engine/SKILL.md in full.

Execute the complete 6-step simulated peer review workflow:

  1. LOCATE & READ the paper (draft.md or paper.tex — use the most recent version)
  2. ASSESS against 7 evaluation dimensions (contribution, theory, method, literature, argumentation, writing, relevance)
  3. GENERATE Reviewer 1 — "The Methodologist" (focus: research design, rigor, validity, replicability)
  4. GENERATE Reviewer 2 — "The Theorist" (focus: contribution, positioning, theoretical depth, novelty)
  5. CALIBRATE recommendations independently (do not harmonize reviewers)
  6. COMPILE & SAVE to simulated_reviews.md with meta-reviewer summary and priority revision checklist

Input

$ARGUMENTS can be:

  • Empty — reviews the most recent draft (draft.md or paper.tex, whichever is newer)
  • File path to a specific manuscript (e.g., @draft_v2.md, @latex/paper.tex)
  • Venue name to calibrate review criteria (e.g., ICIS, MISQ, ECIS, NeurIPS)
  • "journal" or "conference" to adjust review depth and tone accordingly

Output

  • simulated_reviews.md — 2 complete reviewer reports + meta-reviewer synthesis
  • Each review: Summary, Strengths, Weaknesses, Minor Comments, Questions, Recommendation
  • Priority revision checklist (ordered by impact)
  • Ready for /respond-reviewers simulated_reviews.md to process feedback systematically
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. 10d ago First seen · 37 lines · 79 tokens per session scan A e56a13ec4c9b

Subscribe to this mod's changes

review-paper is a command published in the GitHub repository TobiasBlask/open-paper-machine (18 stars, last pushed 5mo ago), licensed MIT. It adds 79 tokens to every session and 463 once invoked, about $0.0004 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.