litlib-literature-workflow

litlib-literature-workflow is a skill for Claude Code, Codex from ganpingzhu904-dev/jlu-literature-agent-mcp. It costs 107 tokens per session (3,189 once invoked), scanned A, original, MIT.

A workflow for finding academic papers, obtaining permitted copies, checking PDFs, and organizing them in Zotero. Zotero is a reference manager, and CARSI, WebVPN, CNKI, and similar services provide institution-based or academic access.

In plain words
What is it for?
Searching approved scholarly databases, acquiring papers using allowed access, checking downloaded PDFs, importing them into Zotero, and searching a local paper collection.
Why use it?
It coordinates several research and local-library steps while avoiding CAPTCHA and paywall bypasses and keeping track of what was verified.

Skill for Claude CodeCodex

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

Good fit Searching approved scholarly databases, acquiring papers using allowed access, checking downloaded PDFs, importing them into Zotero, and searching a local paper collection.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ganpingzhu904-dev/jlu-literature-agent-mcp/litlib-literature-workflow
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 ganpingzhu904-dev/jlu-literature-agent-mcp --skill litlib-literature-workflow
Clone the repo
git clone --depth 1 https://github.com/ganpingzhu904-dev/jlu-literature-agent-mcp

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 litlib-literature-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/ganpingzhu904-dev/jlu-literature-agent-mcp/litlib-literature-workflow/github.svg)](https://agentmods.dev/skills/ganpingzhu904-dev/jlu-literature-agent-mcp/litlib-literature-workflow)
Your own site
<a href="https://agentmods.dev/skills/ganpingzhu904-dev/jlu-literature-agent-mcp/litlib-literature-workflow"><img src="https://agentmods.dev/badge/skills/ganpingzhu904-dev/jlu-literature-agent-mcp/litlib-literature-workflow/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 litlib-literature-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/ganpingzhu904-dev/jlu-literature-agent-mcp/litlib-literature-workflow"><img src="https://agentmods.dev/badge/skills/ganpingzhu904-dev/jlu-literature-agent-mcp/litlib-literature-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,189 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 $0.00107 $0.03189
Opus 5 $0.00053 $0.01595
Sonnet 5 $0.00021 $0.00638
Haiku 4.5 $0.00011 $0.00319

Measured 11d ago against content hash 428adae76ded, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

litlib-literature-workflow 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 11d 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.

skills/litlib-literature-workflow/SKILL.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LitLib Literature Workflow

Purpose

Use this skill as the execution policy for a three-part system:

  1. This skill decides which capability to use, applies compliance and human checkpoints, interprets failures, and records what was verified.
  2. LitLib MCP performs deterministic, local, read-only lookup of metadata, task state, PDF paths, Zotero collections, and paged PDF text.
  3. ZotSeek MCP performs local semantic or hybrid retrieval over a separately maintained Zotero index.

All mutations use the litlib CLI or an explicit human Zotero action. MCP tools do not download papers, change task state, import items, or modify the Zotero library.

Do Not Overclaim

LitLib is an acquisition and local-library workflow, not a complete bibliographic search database. For a topic search, first use the Agent's installed academic database capability (for example PubMed, Crossref, OpenAlex, Semantic Scholar, or another approved scholarly source), retain DOI/PMID and source provenance, then pass identifiers to LitLib. Do not substitute generic web search when an academic database tool is available.

ZotSeek is an external Zotero plugin, not code shipped by LitLib. Its MCP can only search items already covered by the active embedding model. Semantic similarity is retrieval evidence, not evidence that a paper supports a scientific claim.

Locate and Inspect the Installation

Never assume D:\op\projects\literature-library on another machine. Resolve the project in this order:

  1. User-provided project path.
  2. LITLIB_ROOT, if set.
  3. The repository containing pyproject.toml with project name litlib.
  4. An installed litlib executable on PATH.

Before a write workflow, run:

litlib --version
litlib doctor
litlib status

Examples use litlib for readability. In an unactivated source clone, run the equivalent uv run litlib ...; on Windows, MCP clients should use the absolute .venv\Scripts\python.exe with arguments -m litlib.cli mcp so the console-script wrapper is not locked during upgrades.

Read the full file on GitHub · 295 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 295 lines · 107 tokens per session scan A 428adae76ded

Subscribe to this mod's changes

litlib-literature-workflow is a skill published in the GitHub repository ganpingzhu904-dev/jlu-literature-agent-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 3,189 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories