literature-review

literature-review is a skill for Claude Code, Codex from adolinjonathan-bot/zotero-toolkit. It costs 46 tokens per session (1,132 once invoked), scanned A, original, MIT.

A workflow for systematic or scoping literature reviews using a Zotero library. Zotero is a tool for collecting and organizing research references; the workflow covers deduplication, screening, audit records, and PRISMA 2020 counts.

In plain words
What is it for?
Use it to prepare a review library, screen studies against criteria, record decisions, and maintain an auditable review process.
Why use it?
It reduces undocumented screening decisions, incorrect reference counts, and lost reasons for including or excluding studies.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare a review library, screen studies against criteria, record decisions, and maintain an auditable review process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adolinjonathan-bot/zotero-toolkit/literature-review
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.

Any agent
npx skills add adolinjonathan-bot/zotero-toolkit --skill literature-review
Clone the repo
git clone --depth 1 https://github.com/adolinjonathan-bot/zotero-toolkit

Made for: Claude Code, Codex.

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 literature-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/adolinjonathan-bot/zotero-toolkit/literature-review/github.svg)](https://agentmods.dev/skills/adolinjonathan-bot/zotero-toolkit/literature-review)
Your own site
<a href="https://agentmods.dev/skills/adolinjonathan-bot/zotero-toolkit/literature-review"><img src="https://agentmods.dev/badge/skills/adolinjonathan-bot/zotero-toolkit/literature-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 literature-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/adolinjonathan-bot/zotero-toolkit/literature-review"><img src="https://agentmods.dev/badge/skills/adolinjonathan-bot/zotero-toolkit/literature-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,132 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 $0.00046 $0.01132
Opus 5.5 $0.00018 $0.00453
Sonnet 5.5 $0.00009 $0.00226
Haiku 4.5 $0.00005 $0.00113

Measured today against content hash a3b11cd2a9f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

literature-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 today.

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.

agent-skills/literature-review/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Literature Review Skill

Use this skill when conducting a systematic review, scoping review, or structured literature screening over a Zotero library using zotero-mcp-server (and optionally the AutoAttach Zotero plugin).

Core Principles

  1. Never screen or delete silently. Always present proposed deduplications or screening decisions in a structured table and wait for the reviewer to confirm before writing tags, notes, or moving items to Trash.
  2. Exclude standalone attachments from reference counts. Always pass item_type="-attachment" when counting or screening references so standalone PDFs do not inflate PRISMA totals.
  3. Merge tags, never overwrite them. Use zotero_add_tags and zotero_remove_tags rather than zotero_update_item, which replaces the entire tags array.
  4. Keep the audit trail inside the library. Every excluded study at full-text or abstract screening should receive both a structured tag (e.g. SCREENING:Excluded) and a child note (zotero_create_note) stating the primary exclusion reason.

Workflow Stages

Stage 1: Library Preparation & Deduplication

  1. Identify scope: Ask whether the review covers a specific collection (zotero_list_collections) or the entire library.
  2. Find duplicates: Call zotero_find_duplicates (with collection_key if scoped).
  3. Inspect candidate clusters: For each duplicate cluster, call zotero_get_item_children on its members so you never trash the copy that holds the attached PDF or reading notes.
  4. Propose deduplication table: Show:
    • Cluster # and matching evidence (exact DOI, ISBN, or title+author+year)
    • Key to Keep (richest metadata + attachments)
    • Key(s) to Trash
    • Tags/collections to merge onto the kept record
  5. Apply after confirmation:
    • Merge tags via zotero_add_tags and collections via zotero_add_items_to_collection.
    • Trash redundant records via zotero_delete_items (permanent: false).
    • Record the count of duplicates removed for the PRISMA flow diagram.

Read the full file on GitHub · 67 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. today First seen · 67 lines · 46 tokens per session scan A a3b11cd2a9f0

Subscribe to this mod's changes

literature-review is a skill published in the GitHub repository adolinjonathan-bot/zotero-toolkit (1 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,132 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-24.