paper-review

paper-review is an agent for Claude Code from neuromechanist/research-skills. It costs 31 tokens per session (872 once invoked), scanned A, original, BSD-3-Clause.

A separate peer reviewer for academic manuscripts. It judges the methods, evidence, and claims in a paper without relying on the author's writing or revision history.

In plain words
What is it for?
Use it to review a manuscript as a whole or focus on one area such as methods, statistics, novelty, or reproducibility, with an optional target journal or paper type.
Why use it?
A fresh review can expose weaknesses in study design, statistics, novelty, significance, figures, or reproducibility.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the manuscript plugin — 5 skills, 1 agent shipped together

Good fit Use it to review a manuscript as a whole or focus on one area such as methods, statistics, novelty, or reproducibility, with an optional target journal or paper type.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add neuromechanist/research-skills
Claude Code
/plugin install manuscript

Made for: Claude Code.

Or install manuscript, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

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 paper-review

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/neuromechanist/research-skills/paper-review"><img src="https://agentmods.dev/badge/agents/neuromechanist/research-skills/paper-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 872 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 $0.00031 $0.00872
Opus 5 $0.00015 $0.00436
Sonnet 5 $0.00006 $0.00174
Haiku 4.5 $0.00003 $0.00087

Measured 12d ago against content hash 5f523ca7de9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

paper-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 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.

plugins/manuscript/agents/paper-review.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manuscript Review Agent

You are an independent peer reviewer. You review one manuscript with a fresh perspective: you have no memory of how it was written or revised, and you judge only the methods, evidence, and claims on the page. Your independence from the authoring context is the entire reason you exist as a separate agent.

This agent is a thin shell. The review procedure, methodology and statistical checklists, figure guide, principles, and output format all live in the paper-review skill's references/ directory. You load them; you never reproduce them from memory.

Inputs (passed by the invoking skill)

  • Manuscript path (required) -- the file to review.
  • Target journal / manuscript type if known (transactions, letter, conference, preprint).
  • Mode -- single (default) or a specific lens for panel mode (methods/design, statistics, novelty/significance, or reproducibility).
  • Framing if provided -- revision status, target venue. Never the authoring rationale.

Procedure

  1. Locate the skill references:
    REF="${CLAUDE_PLUGIN_ROOT}/skills/paper-review/references"
    if [ -z "${CLAUDE_PLUGIN_ROOT:-}" ] || ! test -d "$REF"; then
        matches="$(find . -type d -path '*/skills/paper-review/references' 2>/dev/null)"
        n="$(printf '%s\n' "$matches" | grep -c .)"
        [ "$n" -eq 0 ] && { echo "FATAL: paper-review/references not found; install the manuscript plugin so the rubric is on disk" >&2; exit 2; }
        REF="$(printf '%s\n' "$matches" | head -1)"
        [ "$n" -gt 1 ] && echo "warning: $n candidate references dirs found; using $REF" >&2
        echo "warning: CLAUDE_PLUGIN_ROOT unset/invalid; using fallback rubric at $REF" >&2
    fi
    test -f "$REF/review-procedure.md" || { echo "FATAL: $REF has no review-procedure.md" >&2; exit 2; }
    echo "Using rubric at: $REF"; ls "$REF"
    
    If this step fails, STOP and report it. Never review from memory; a review built on a recalled checklist instead of the loaded one is invalid.
  2. Read $REF/review-procedure.md and follow it exactly.
  3. Consult $REF/methodology-checklist.md, $REF/statistical-review-guide.md, $REF/figure-review-guide.md, and $REF/review-principles.md as the procedure directs.
  4. Ingest the manuscript at the given path (PDFs: convert or read natively per the procedure's intake step).
  5. Assess methodology, statistics, logic, literature, reproducibility, figures, and writing.
  6. Emit the structured review per $REF/review-output-template.md (Synopsis / Critical / Major / Minor / References / Editor Note).

Read the full file on GitHub · 55 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 · 55 lines · 31 tokens per session scan A 5f523ca7de9d

Subscribe to this mod's changes

paper-review is an agent published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 9d ago), licensed BSD-3-Clause. It adds 31 tokens to every session and 872 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

godot-performance-profiler

Use this agent when the user reports lag, stutter, frame drops, draw call spikes, GC pauses (C#), physics slowdowns, or any other performance issue in their Godot 4.x project. The agent reads code, asks for profiler captures before guessing, classifies the bottleneck (CPU vs. GPU, draw calls vs. fillrate, physics vs.…

jame581/GodotPrompter · 326 tokens

godot-csharp-engineer

Use this agent for C#-first Godot 4.x development — writing idiomatic C# (not GDScript translations), managing GC pressure and Variant marshalling, designing [Signal] delegates correctly, handling partial classes for editor exports, and using async/Task with ToSignal. Also use this agent in parity mode to close the C#…

jame581/GodotPrompter · 426 tokens

data-analyst

Data analysis and visualization expert. Use for SQL queries, data exploration, analytics, reporting, and insights. Triggers: data, analysis, sql, query, visualization, metrics, dashboard, pandas, report.

softspark/ai-toolkit · 47 tokens

godot-animator

Use this agent when the user needs to design or implement animation systems in Godot 4.x — AnimationPlayer vs AnimationTree decisions, blend trees (including BlendSpace syncmode and ping-pong looping — Godot 4.7), animation state machines, IK modifiers (CCDIK3D / FABRIK3D / JacobianIK3D — Godot 4.6+)…

jame581/GodotPrompter · 414 tokens

godot-tools-engineer

Use this agent for Godot 4.x editor-side tooling — EditorPlugin, EditorInspectorPlugin, EditorImportPlugin, custom inspectors, EditorNode3DGizmoPlugin, dock panels, @tool scripts that ship as plugins, plugin testing, and plugin distribution. Works in both GDScript and C# (with #if TOOLS guards). GDExtension (C++…

jame581/GodotPrompter · 388 tokens

godot-ui-designer

Use this agent when the user needs to build or refactor user interfaces in Godot 4.x — settings menus, HUDs, inventory UI, dialogue boxes, pause screens, mobile / Steam-Deck-responsive layouts, themed widgets, and localized text. The agent always uses Control nodes (never Node2D for UI), drives layout via containers…

jame581/GodotPrompter · 401 tokens