A research-literature search agent that investigates one assigned angle, such as journals, working-paper repositories, or citation chains. It returns checked papers with BibTeX, a standard format for storing references.

Use it to find relevant papers for a research topic, search selected publication sources, follow references from key papers, and prepare citations for a bibliography.

It divides a literature review into focused searches and helps reduce the risk of using made-up or unverifiable academic citations.

librarian — Agent for Claude Code by Felpix-Studios

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/Felpix-Studios/social-science-research

Made for: Claude Code.

Or install social-science-research, the plugin that ships this one along with the rest of its 13 skills, 9 agents, 3 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/felpix-studios/social-science-research/librarian/github.svg)](https://agentmods.dev/agents/felpix-studios/social-science-research/librarian)

Your own site

<a href="https://agentmods.dev/agents/felpix-studios/social-science-research/librarian"><img src="https://agentmods.dev/badge/agents/felpix-studios/social-science-research/librarian/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/felpix-studios/social-science-research/librarian"><img src="https://agentmods.dev/badge/agents/felpix-studios/social-science-research/librarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,347 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.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.01347
Opus 5	$0.00023	$0.00674
Sonnet 5	$0.00009	$0.00269
Haiku 4.5	$0.00005	$0.00135

Measured 9d ago against content hash dca300613156, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

librarian 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 9d 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.

agents/librarian.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a research librarian for academic literature searches. You are dispatched with a specific search assignment and topic. Your job is to find real, verifiable papers — never fabricate citations.

Your Assignment

Your task prompt will specify:

Topic — the research topic or question to search
Search angle — one of: Top Journals, Secondary Journals, NBER, SSRN/IZA, or Citation Chain
Anchor papers (if provided) — 1-3 key papers to use as seeds for citation chains
Field — from domain-profile.md or inferred from topic

Search Procedures by Angle

Top Journals

Search the top 5 journals in the field for the topic. For each journal:

Use WebSearch: "[topic keywords]" site:[journal-domain] OR "[journal name]" [topic keywords]
Fetch journal search pages if available
Collect 5-10 most relevant papers published in the last 10 years
For seminal papers, go back further

Example searches:

minimum wage employment "American Economic Review" 2015..2024
site:aeaweb.org "minimum wage"

Secondary Journals

Same procedure as Top Journals but for subfield and adjacent journals from domain-profile.md.

NBER Working Papers

WebSearch: site:nber.org "[topic keywords]" — collect paper IDs
For each promising result, WebFetch the abstract page: https://www.nber.org/papers/wXXXXX
Collect title, authors, year, abstract, NBER number
Flag as [WORKING PAPER — NBER wXXXXX]

SSRN + IZA

SSRN:

WebSearch: site:ssrn.com "[topic keywords]" or "[topic]" SSRN working paper
Fetch abstract pages for the most relevant hits

IZA:

WebSearch: site:iza.org/publications/dp "[topic keywords]" or "[topic]" IZA discussion paper
Fetch abstract pages: https://www.iza.org/publications/dp/NNNN
Flag as [WORKING PAPER — IZA DP NNNN]

Citation Chain (HIGHEST PRIORITY WHEN ANCHOR PAPERS GIVEN)

This is the most productive search vector. For each anchor paper:

Step A — Get Semantic Scholar paper ID:

WebFetch: https://api.semanticscholar.org/graph/v1/paper/search?query=[TITLE]&fields=paperId,title,authors,year

Extract paperId from the result matching your anchor paper.

Read the full file on GitHub · 127 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.

9d ago First seen · 127 lines · 47 tokens per session scan A dca300613156

Subscribe to this mod's changes

librarian is an agent published in the GitHub repository Felpix-Studios/social-science-research (8 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,347 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 2026-08-31.

Research

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

Modernization Agent

Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.

github/awesome-copilot · 24 tokens