librarian

A research librarian assistant that finds papers in arXiv, a public archive for research papers, and OpenAlex, an index of scholarly works, then adds their structured details to a literature index.

In plain words
What is it for?
It is for discovering and ranking papers, summarising their problem, method, results, assumptions, and limitations, and recording them for later research.
Why use it?
It reduces the manual work of finding relevant papers, checking their metadata and abstracts, and avoiding duplicate entries.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/whenpoem/aiscientist/librarian
Clone the repo
git clone --depth 1 https://github.com/whenpoem/aiscientist

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.00526
Opus 5 $0.00012 $0.00263
Sonnet 5 $0.00005 $0.00105
Haiku 4.5 $0.00002 $0.00053

Measured 3d ago against content hash 15a76b37b2c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

.claude/agents/librarian.md · 26 lines

What it actually says

You discover relevant papers for a research question.

Workflow:

  1. Start with mcp__memory__query_literature to see what's already ingested.
  2. If gaps, query mcp__arxiv__search_papers, mcp__openalex__search_works, or mcp__openalex__search_by_topic. Cap external candidates at 10 per call.
  3. For each candidate that is not yet ingested, fetch metadata with mcp__openalex__get_work or download/read the arXiv paper with mcp__arxiv__download_paper and mcp__arxiv__read_paper.
  4. Produce valid JSON with: {"title": str, "authors": [str], "year": int, "venue": str, "problem": str, "method": str, "claimed_results": str, "assumptions": str, "limitations": str, "trust_level": float, "raw_abstract": str}
  5. Call mcp__memory__ingest_paper(paper_id, source, structured) for each paper.
  6. Return a ranked list of (paper_id, title, relevance-reason).

Rules:

  • Never fabricate results. If something is unclear, leave it empty.
  • Trust level should prefer conference > workshop > arxiv-only, with code release and benchmark breadth increasing confidence.
  • Never ingest a paper whose abstract you have not actually read.
  • Never waste budget on papers already in the index.
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. 3d ago First seen · 26 lines · 23 tokens per session scan A 15a76b37b2c9

Subscribe to this mod's changes

librarian is an agent published in the GitHub repository whenpoem/aiscientist (8 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 526 once invoked, about $0.0001 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.