zotero-review

zotero-review is a command for Claude Code from Galaxy-Dawn/claude-scholar. It costs 32 tokens per session (1,040 once invoked), scanned A, original, MIT.

A command that reads research papers from a Zotero collection, a library for organizing academic references, and combines their findings into an Obsidian knowledge base or a Markdown review file.

In plain words
What is it for?
Use it to create literature reviews and related-work drafts from papers saved in Zotero.
Why use it?
It removes the need to open and summarize each paper by hand, while providing a fallback when full paper text is unavailable.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-scholar plugin — 45 skills, 34 commands, 6 agents, 5 hooks shipped together

Good fit Use it to create literature reviews and related-work drafts from papers saved in Zotero.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/galaxy-dawn/claude-scholar/zotero-review
About the project

Claude Scholar is a semi-automated research assistant for academic research and software development, supporting literature review, coding, experiments, reporting, writing, and project knowledge management. Computer science and AI researchers use it across the research workflow with several coding-agent platforms; the catalogue contains its skills, commands, agents, hooks, plugin, and instruction.

Galaxy-Dawn/claude-scholar · 5,419 stars · on GitHub

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/Galaxy-Dawn/claude-scholar

Made for: Claude Code.

Or install claude-scholar, the plugin that ships this one along with the rest of its 45 skills, 34 commands, 6 agents, 5 hooks.

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 zotero-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/galaxy-dawn/claude-scholar/zotero-review/github.svg)](https://agentmods.dev/commands/galaxy-dawn/claude-scholar/zotero-review)
Your own site
<a href="https://agentmods.dev/commands/galaxy-dawn/claude-scholar/zotero-review"><img src="https://agentmods.dev/badge/commands/galaxy-dawn/claude-scholar/zotero-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 zotero-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/galaxy-dawn/claude-scholar/zotero-review"><img src="https://agentmods.dev/badge/commands/galaxy-dawn/claude-scholar/zotero-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,040 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 $0.00032 $0.01040
Opus 5 $0.00016 $0.00520
Sonnet 5 $0.00006 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured 12d ago against content hash cd1430547331, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

zotero-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.

commands/zotero-review.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/zotero-review - Zotero Collection Literature Analysis

Read and analyze papers in the Zotero collection "$collection", with analysis depth "$depth".

Default target

  • Preferred target: the bound Obsidian project knowledge base
  • Fallback target: related-work-draft.md in the current working directory

Workflow

Step 0: Resolve the project context

  1. If the current repo is already bound to an Obsidian project KB, use that project root.
  2. If the repo looks like a research project but is not bound yet, bootstrap it first.
  3. If there is no project binding, generate the review in the working directory.

Step 1: Locate and read the Zotero collection

  1. Call mcp__zotero__zotero_get_collections to find the matching collection.
  2. Call mcp__zotero__zotero_get_collection_items to get all papers.
  3. For each paper:
    • call mcp__zotero__zotero_get_item_metadata with include_abstract: true
    • call mcp__zotero__zotero_get_item_fulltext when available
    • use abstract metadata as fallback when PDF full text is unavailable
  4. If MCP transport fails but a local zotero-mcp checkout is available, use the local Python fallback instead of aborting.
  5. Treat Zotero webpage items as weak-source entries unless they clearly expose full paper metadata and useful full text. Abstract-only or placeholder pages can appear in coverage summaries, but cannot support Knowledge, Writing, manuscript, or rebuttal claims.

Step 2: Ensure detailed paper notes exist

Before high-level synthesis, ensure the collection has durable paper notes.

If the project is Obsidian-bound:

  • create or update Sources/Papers/*.md canonical notes first
  • keep one canonical paper note per paper whenever possible
  • align notes to the canonical schema (Claim / Method / Evidence / Limitation / Direct relevance to repo / Relation to other papers)
  • update the best matching Knowledge/ literature synthesis notes
  • refresh Maps/literature.canvas
  • update a collection inventory note with item -> note mapping and coverage summary

Read the full file on GitHub · 103 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 · 103 lines · 32 tokens per session scan A cd1430547331

Subscribe to this mod's changes

zotero-review is a command published in the GitHub repository Galaxy-Dawn/claude-scholar (5,419 stars, last pushed 15d ago), licensed MIT. It adds 32 tokens to every session and 1,040 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.