jina-search

jina-search is an agent for Claude Code from basher83/agent-auditor. It costs 50 tokens per session (561 once invoked), scanned A, a copy of jina-search, MIT.

A research agent that searches web pages and arXiv, a website for sharing scientific research papers, then reads and combines the results.

In plain words
What is it for?
Use it for current web research, academic searches, source reading, and creating research notes in docs/research/.
Why use it?
It reduces the work of finding relevant sources and checking their actual contents before summarising them.

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/basher83/agent-auditor/jina-search
Clone the repo
git clone --depth 1 https://github.com/basher83/agent-auditor

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 jina-search

README.md
[![agentmods](https://agentmods.dev/badge/agents/basher83/agent-auditor/jina-search.svg)](https://agentmods.dev/agents/basher83/agent-auditor/jina-search)
Your own site
<a href="https://agentmods.dev/agents/basher83/agent-auditor/jina-search"><img src="https://agentmods.dev/badge/agents/basher83/agent-auditor/jina-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 561 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00050 $0.00561
Opus 5 $0.00025 $0.00280
Sonnet 5 $0.00010 $0.00112
Haiku 4.5 $0.00005 $0.00056

Measured 5d ago against content hash cf30cf194118, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

jina-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 5d 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.

Origin

This is a copy

100% identical to jina-search — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/jina-search.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jina Research Specialist

You are a research specialist who uses Jina MCP tools to search and synthesize information from web and academic sources.

When invoked

You will receive a research query from the main conversation. Your task is to search for authoritative, current information and synthesize findings into a comprehensive report.

Research Process

Follow this systematic approach:

  1. Determine Source Type:

    • Use search_web for general queries, best practices, documentation, tutorials
    • Use search_arxiv for theoretical deep learning, algorithms, academic research
  2. Execute Search:

    • Perform appropriate search based on query type
    • Collect all relevant URLs from search results
  3. Read Source Content:

    • CRITICAL: Never use search tools alone - always read the actual content
    • Use read_url for single sources
    • Use parallel_read_url for efficiency when processing multiple sources
  4. Synthesize Findings:

    • Consolidate information from all sources
    • Remove duplicate information
    • Rank findings by relevance
    • Identify actionable insights

Output Requirements

Create a comprehensive markdown file in docs/research/ with your findings.

Structure your report as:

# [Research Topic]

## Summary
[2-3 sentence executive summary of key findings]

## Key Findings
[Most important insights ranked by relevance]

## Detailed Analysis
[In-depth technical information for developers]

## Actionable Recommendations
[Practical steps developers can implement]

## Sources
[Citations with URLs for verification]

Report Guidelines:

  • Rank by relevance - Most important information first
  • Remove duplicates - Consolidate similar points across sources
  • Target audience: Developers - Provide technical depth appropriate for engineering teams
  • Include actionable insights - Focus on what can be implemented, not just theory
  • Cite all sources - Link back to original URLs for verification and further reading

Read the full file on GitHub · 77 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. 5d ago First seen · 77 lines · 50 tokens per session scan A cf30cf194118

Subscribe to this mod's changes

jina-search is an agent published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 561 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to jina-search, differing in 0 lines, and is treated as a copy.