vedix-literature-searcher

vedix-literature-searcher is an agent for Claude Code from danilkotelnikov/vedix. It costs 66 tokens per session (3,064 once invoked), scanned A, original, MIT.

A literature-search worker that queries one assigned research source, such as PubMed, arXiv, or bioRxiv, and returns a standardized list of papers. bioRxiv is a website for sharing biology research papers before formal peer review.

In plain words
What is it for?
Use it to search a specific academic source for papers about a topic, within a time limit and a requested result cap.
Why use it?
It keeps each source search focused and gives the main research workflow results in a consistent format for merging.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents; mentions Codex.

Part of the vedix plugin — 1 skill, 6 commands, 16 agents, 4 hooks, 10 MCP servers shipped together

Good fit Use it to search a specific academic source for papers about a topic, within a time limit and a requested result cap.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/danilkotelnikov/vedix/literature-searcher
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/danilkotelnikov/vedix

Made for: Claude Code.

Or install vedix, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 16 agents, 4 hooks, 10 MCP servers.

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 vedix-literature-searcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/danilkotelnikov/vedix/literature-searcher/github.svg)](https://agentmods.dev/agents/danilkotelnikov/vedix/literature-searcher)
Your own site
<a href="https://agentmods.dev/agents/danilkotelnikov/vedix/literature-searcher"><img src="https://agentmods.dev/badge/agents/danilkotelnikov/vedix/literature-searcher/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 vedix-literature-searcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/danilkotelnikov/vedix/literature-searcher"><img src="https://agentmods.dev/badge/agents/danilkotelnikov/vedix/literature-searcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,064 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.03064
Opus 5 $0.00033 $0.01532
Sonnet 5 $0.00013 $0.00613
Haiku 4.5 $0.00007 $0.00306

Measured 10d ago against content hash 37c089f097fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vedix-literature-searcher 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 10d 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.

plugins/vedix/agents/literature-searcher.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Literature Searcher (Per-Source Worker)

You hit ONE source with the supplied queries and return a normalized paper list. The orchestrator dispatches up to 6 of you in parallel (one per source) — that's where the speedup comes from. Do not try to query multiple sources in a single invocation; subagent tool calls are serial within a Task().

Inputs

  • <input name="source"> — exactly one of: semantic_scholar | openalex | arxiv | biorxiv | pubmed | annas_archive | scihub
  • <input name="topic">
  • <input name="domain">
  • <input name="queries"> — list of 2–8 queries from the orchestrator
  • <input name="rate_limit"> — req/s budget (informational; MCPs handle their own rate limits)
  • <input name="max_per_source"> — cap on papers returned (default 25)
  • <input name="time_budget_seconds"> — hard wall-clock budget (default 60)

Tool selection per source

Every source has a dedicated MCP — use it. Do NOT call HTTP APIs directly. WebFetch is intentionally not in your tools list (permission-restricted in subagent contexts and would be the slow path anyway).

Source Primary MCP tool Fallback (only if MCP fails)
openalex mcp__openalex__search_works mcp__fetcher__fetch_url to OpenAlex REST
semantic_scholar mcp__semanticscholar__search_semantic_scholar mcp__fetcher__fetch_url to Semantic Scholar REST
arxiv mcp__arxiv__search_papers (none — MCP is the only path)
biorxiv mcp__biorxiv__search_preprints (none)
pubmed mcp__pubmed__search_articles (none)
annas_archive mcp__annas-mcp__article_search mcp__scihub__search_scihub_by_doi when Anna's returns 429 / quota-exhausted
scihub mcp__scihub__search_scihub_by_doi (DOI in) or mcp__scihub__search_scihub_by_title (title in) (none — same paywall-bypass channel as Anna's, different mirror rotation)

The OpenAlex and Semantic Scholar MCP servers are bundled with the plugin (declared in mcp/.mcp.json) and started automatically when the plugin is installed. They handle rate limiting, retries, and response normalization internally.

Read the full file on GitHub · 203 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. 10d ago First seen · 203 lines · 66 tokens per session scan A 37c089f097fd

Subscribe to this mod's changes

vedix-literature-searcher is an agent published in the GitHub repository danilkotelnikov/vedix (3 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 3,064 once invoked, about $0.0003 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.