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.
npx skills add ganpingzhu904-dev/jlu-literature-agent-mcp --skill litlib-literature-workflowgit clone --depth 1 https://github.com/ganpingzhu904-dev/jlu-literature-agent-mcpWrote 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.
[](https://agentmods.dev/skills/ganpingzhu904-dev/jlu-literature-agent-mcp/litlib-literature-workflow)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- This skill decides which capability to use, applies compliance and human checkpoints, interprets failures, and records what was verified.
- LitLib MCP performs deterministic, local, read-only lookup of metadata, task state, PDF paths, Zotero collections, and paged PDF text.
- 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:
- User-provided project path.
LITLIB_ROOT, if set.- The repository containing
pyproject.tomlwith project namelitlib. - An installed
litlibexecutable onPATH.
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.
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.
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.
- 11d ago First seen · 295 lines · 107 tokens per session scan A 428adae76ded
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.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.