What is paper-navigator?

A research-paper finder and reader for papers from arXiv, a public archive of scientific preprints, and Semantic Scholar, a research database. It searches by keywords, citations, related-paper recommendations, and snippets, then judges relevance using a written set of criteria.

Use it to find one paper or a group of papers, investigate related work, follow citations, get paper excerpts, and read selected papers at different levels of detail.

It reduces the work of finding relevant papers and deciding which ones are worth reading in depth.

paper-navigator — Skill for Claude Code by EvoScientist

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 EvoScientist/EvoSkills --skill paper-navigator

Clone the repo

git clone --depth 1 https://github.com/EvoScientist/EvoSkills

Made for: Claude Code.

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/skills/evoscientist/evoskills/paper-navigator.svg)](https://agentmods.dev/skills/evoscientist/evoskills/paper-navigator)

Your own site

<a href="https://agentmods.dev/skills/evoscientist/evoskills/paper-navigator"><img src="https://agentmods.dev/badge/skills/evoscientist/evoskills/paper-navigator.svg" alt="Measured on agentmods" height="20"></a>

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,712 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00105	$0.06712
Opus 5	$0.00053	$0.03356
Sonnet 5	$0.00021	$0.01342
Haiku 4.5	$0.00011	$0.00671

Measured 8d ago against content hash 44713448eaa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

paper-navigator 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 8d ago.

The scan reads SKILL.md. This mod also ships 19 executable files (scripts/arxiv_monitor.py, scripts/author_search.py, scripts/citation_traverse.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/paper-navigator/SKILL.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper Navigator

Find and read academic papers. Route by intent, judge by relevance.

        User
         │
         ▼
   ┌── Router ──┐
   │            │
   ▼            ▼
 POINT      LIST/ITERATIVE
(1 paper)   (Probe + up to 3 paper rounds:
             R2 breadth / R3 deepen / R4 close)

The agent does relevance judgment — no LLM-as-judge is called, no numeric scoring. You author the rubric, you triage each paper, you rank by relevance.

Setup

Scripts at skills/paper-navigator/scripts/. Run via python skills/paper-navigator/scripts/<name>.py.

arXiv access (arxiv_monitor, scholar_search fallback) uses the DeepXiv SDK: pip install deepxiv-sdk, then deepxiv token once to provision a free API token (saved to ~/.env). The skill reads the token from DEEPXIV_API_TOKEN/DEEPXIV_TOKEN in the environment, or from ./.env / ~/.env.

Env var	Used by	Notes
`S2_API_KEY`	All S2 scripts	Without it: `scholar_search` falls back to arXiv (via DeepXiv); `citation_traverse` / `recommend` / `snippet_search` are disabled
`DEEPXIV_API_TOKEN`	`arxiv_monitor`, `scholar_search` fallback	Get a free token: `deepxiv token` (writes `~/.env`). Also read from `DEEPXIV_TOKEN` and `./.env`/`~/.env`. ~10,000 req/day
`JINA_API_KEY`	`fetch_paper`	Free tier works without key
`GITHUB_TOKEN`	`github_search`, `find_code`	Higher rate limits
`PAPER_NAV_PAPERS_DIR`	`fetch_paper` full text	No default — set or pass `--metadata-only`

Full env-var list: references/env-vars.md.

Five Red Lines (always)

Track history. Don't re-run a query you already ran. Empty result → change angle, not synonyms.
Search a gap, not a vibe. Every query maps to one missing piece of information. No stacked-keyword bags.
One query = one concept. Split comparisons (A vs B), multi-property asks, and multi-year spans into separate calls.
Never hallucinate. Every fact (title, author, year, citation count, content) comes from a tool result.
Quote-or-zero. When you claim a paper meets a criterion, quote a ≤80-char span from its abstract / tldr / snippet. No quote → do not claim the paper meets that criterion. (This guards against hallucination; it does not drive a numeric score.)

Read the full file on GitHub · 378 lines

Files

What ships with it

29 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.

8d ago First seen · 378 lines · 105 tokens per session scan A 44713448eaa6

Subscribe to this mod's changes

paper-navigator is a skill published in the GitHub repository EvoScientist/EvoSkills (436 stars, last pushed 7d ago), licensed Apache-2.0. It adds 105 tokens to every session and 6,712 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 2026-08-30.

Research Scientific ai-agent ai4science skills vibe-research

deltasci

Two-perspective co-reasoning for AI4Science hypothesis generation. Runs a structured 4-round dialogue between a domain scientist (parameterized by a domain pack) and an ML engineer, producing a grounded, falsifiable research hypothesis that is honest about the AI's training-distribution edges. Domain-agnostic via…

boheling/deltasci · 117 tokens

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

EvoScientist/EvoScientist · 63 tokens

bio-ortholog-inference

Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…

PKU-YuanGroup/OpenAI4S · 141 tokens

bioprobench

Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.

PKU-YuanGroup/OpenAI4S · 46 tokens

arxiv-package

Package a TeX/LaTeX project into a clean tarball or zip for arXiv upload: file selection, build-artifact exclusion, 00README.XXX generation, ancillary file organization, archive validation. Triggers on: "package for arXiv", "create arXiv tarball", "bundle submission", "zip for arXiv", "prepare arXiv upload", "arXiv…

Mathews-Tom/armory · 105 tokens

paper2poster

Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader content quiz. Use when the user wants…

QuZhan51496/paper2anything · 76 tokens