semantic-scholar-search

semantic-scholar-search is a skill for Claude Code from pantheon-org/tekhne. It costs 81 tokens per session (1,719 once invoked), scanned A, original, MIT.

A search tool for finding academic papers and retrieving information about papers, authors, and citation links. Semantic Scholar is a research database with an official API.

In plain words
What is it for?
Use it to find papers, look up a paper by DOI or identifier, inspect an author's publications, or find papers that cite or reference another paper.
Why use it?
It avoids manual web scraping and gives structured results when you need reliable paper or citation information.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to find papers, look up a paper by DOI or identifier, inspect an author's publications, or find papers that cite or reference another paper.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pantheon-org/tekhne/semantic-scholar-search
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 pantheon-org/tekhne --skill semantic-scholar-search
Clone the repo
git clone --depth 1 https://github.com/pantheon-org/tekhne

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.

agentmods badge for semantic-scholar-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/pantheon-org/tekhne/semantic-scholar-search/github.svg)](https://agentmods.dev/skills/pantheon-org/tekhne/semantic-scholar-search)
Your own site
<a href="https://agentmods.dev/skills/pantheon-org/tekhne/semantic-scholar-search"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/semantic-scholar-search/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 semantic-scholar-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/pantheon-org/tekhne/semantic-scholar-search"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/semantic-scholar-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,719 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.01719
Opus 5 $0.00041 $0.00860
Sonnet 5 $0.00016 $0.00344
Haiku 4.5 $0.00008 $0.00172

Measured 9d ago against content hash 73149e49615f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

semantic-scholar-search 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/semantic-scholar-search.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/documentation/research/semantic-scholar-search/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search Semantic Scholar for papers, fetch structured metadata by paper ID or DOI, profile authors, and traverse citation graphs. Uses the official Semantic Scholar API — no scraping, structured results, free to use.

When to Use

  • Discovering papers on a topic before running triage-paper
  • Resolving an arxiv ID or DOI to full metadata during triage-paper step 1
  • Fetching papers that cite or are cited by a known paper
  • Profiling an author to find their key publications
  • Preferred over google-scholar-search whenever both are available

When Not to Use

  • The semantic-scholar MCP server is configured — optionally prefer it over this script; the MCP returns the same data with less setup
  • The paper is in a biomedical domain not covered by Semantic Scholar — consider PubMed instead
  • You need Google Scholar–exclusive sources (patents, grey literature) — use google-scholar-search

Mindset

This is a structured API, not a search engine — treat it accordingly.

  1. IDs over titles: a gotcha is using a paper title as the --paper-id flag. The paper subcommand requires a Semantic Scholar paper ID, arxiv ID (prefix arXiv:), or DOI. Titles go to search.
  2. Author IDs, not names: the author subcommand requires a Semantic Scholar author ID. A common pitfall is passing a name and getting "not found". Use search first to locate the author ID.
  3. Rate limits apply without a key: 100 requests per 5 minutes without an API key. NEVER issue search loops that exhaust the quota; optionally set SEMANTIC_SCHOLAR_API_KEY to increase limits.

Workflow

1. Choose the right subcommand

Goal Subcommand Key flag
Keyword discovery search --query
Full metadata for a known paper paper --paper-id (SS ID, arXiv:NNNN, or DOI)
Author publications and h-index author --author-id (Semantic Scholar ID)
Papers citing or cited by a paper citations --paper-id + --type

Read the full file on GitHub · 144 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.

  1. 9d ago First seen · 144 lines · 81 tokens per session scan A 73149e49615f

Subscribe to this mod's changes

semantic-scholar-search is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 1,719 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

calculator

Evaluate mathematical expressions and unit conversions. Handles arithmetic, percentages, exponents, and common unit conversions (temperature, distance, weight). No external dependencies.

NVIDIA/SkillEvaluator · 32 tokens

figure-rhetoric

Evaluate whether figures and plots in a manuscript effectively communicate the claims they support. Audits chart-type fit, axis design, visual hierarchy, data density, caption interpretation, perceptual accuracy, and narrative arc across 8 dimensions. Triggers on: "do my figures work", "check my plots", "are my graphs…

Mathews-Tom/armory · 123 tokens

manuscript-provenance

Computational provenance audit verifying every number, table, and figure in a manuscript derives from code, not manual entry. Triggers on: "check provenance", "verify reproducibility", "audit my pipeline", "are my numbers from code", "provenance audit". Companion to manuscript-review (prose audit).

Mathews-Tom/armory · 70 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

paper-planning

Guides pre-writing planning for academic papers with 4 structured steps: story design (task-challenge-insight-contribution-advantage), experiment planning (comparisons + ablations), figure design (pipeline + teaser), and 4-week timeline management. Includes counterintuitive planning tactics (write a mock rejection…

EvoScientist/EvoSkills · 166 tokens

iterate-ml-experiment

Owns the iteration loop on top of an ML workspace: the journal/JOURNAL.md index and the per-experiment journal/NNshortname.md design notes that must be drafted and approved by the user before experiments/NNshortname.py is created. Drives the propose → iterate → approve → implement → record loop; dispatches to…

probabl-ai/skills · 422 tokens