BioResearcher Plugin

OpenCode plugin that adds agents and tools for biomedical and pharmaceutical research.

Overview

No nonsense and powerful. Agents and tools that just work for your typical biomedical and pharmaceutical research needs.

Tab to activate and start asking right away:

• The Bioresearcher Agent is jack-of-all-trades.
• The BioresearcherDR Agent is a specialist for biomed/pharma deep research (DR).

Agents

BioresearcherDR

By default, it will conduct highly detailed and in-depth research, easily surpassing all general purpose LLM applications.

To reduce research depth and make research process faster, start your question with light-research:

light-research Significance of KRAS for cancer?

To skip the Question-Clarification cycle, prompt your question with no-interview:

no-interview light-research Significance of KRAS for cancer?

Tools

Table Tools

Manipulate Excel, CSV, and ODS files with precision and smart parsing for dates, numbers, and data types.

Enable LLMs to wrangle huge tables WITHOUT overwhelming model context.

What are tools for table processing?
What are column names in XXX.xlsx?
Analyze XXX.xlsx - group by Y column, and report unique values of Z column.

Calculator

Evaluate mathematical expressions with full support for brackets, powers, and scientific notation.

Make your model accurate with numbers. No more 3.11 > 3.9 nor 1+2=5.

Use the calculator tool: (3+1.5*6-1/2)^3

Blocking Timer

Pause execution for testing or pacing operations.

Respect API rate limits. No more IP bans/blocks.

Query XXX API. You MUST include a 0.5 second delay between two API calls with the blockingTimer tool.

PubMed Parser

Parse PubMed XML files to markdown or Excel format. Supports .xml and .xml.gz files.

Analyze years of publication articles in one go. Simple and powerful.

Download pubmed article data from https://ftp.ncbi.nlm.nih.gov/pubmed/updatefiles/pubmed26n1340.xml.gz and parse to Excel format.

Reference: PubMed Download Data.

OBO Parser

Parse OBO (Open Biological and Biomedical Ontology) files to CSV format. Handles Term, Typedef, and Instance frames.

Flatten complex ontologies into analysis-ready tables.

Parse go.obo file and convert to CSV using parse_obo_file tool.

Reference: OBO Format.

JSON Tools

Extract, validate, and infer JSON schemas from data.

Robust JSON handling for LLM workflows.

Extract JSON from output.md using jsonExtract tool.
Validate data.json against schema.json using jsonValidate tool.
Infer schema from sample.json using jsonInfer tool.

Database Tools

Query MySQL and MongoDB databases with read-only access.

Explore your data warehouse without leaving the conversation.

List all tables in the database.
Describe the schema for table users.
Query orders placed in the last 30 days.

Configuration via env.jsonc in working directory. Use the env-jsonc-setup skill for guided setup.

Skills

Skills are reusable prompt templates discovered from multiple paths:

| Path | Scope | |------|-------| | .opencode/skills/ | Project | | ~/.config/opencode/skills/ | Global | | .claude/skills/ | Claude Code compatible | | .agents/skills/ | Agents compatible |

This plugin provides a skill tool that overrides Opencode's built-in to support plugin-shipped skills.

See README in tools/skill for full documentation.

Supplied skills

• demo-skill: showcase skill tool mechanisms.
• python-setup-uv: setup python runtime in your working directory with uv.
• pubmed-weekly: automated download of pubmed daily update files over the past one week.
• long-table-summary: batch-process large tables using parallel subagents for summarization.
• bioresearcher-core: core patterns and utilities (retry, JSON tools, subagent waves) for skill development.
• env-jsonc-setup: guided setup for database connection configuration (db-tools).

Prompt the following and follow along:

Setup python uv with skill

Installation

Add the plugin to your opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": [
    "@yeyuan98/opencode-bioresearcher-plugin",
  ],
  "mcp": {
    "biomcp": {
      "type": "local",
      "command": ["uv", "run", "--with", "biomcp-python", "biomcp", "run"],
      "enabled": true,
      "timeout": 120000
    }
  }
}

BioMCP is absolutely required and might take time to load. You will need to have uv installed on your system too. Refer to BioMCP guide for details.

Common Issues and Solutions

| Issue | Solution | |-------|----------| | Agent not appearing | Check plugin in opencode.json is typed correctly | | BioMCP tool failures | Make sure you have BioMCP installed and enabled | | Research taking a long time | Check whether subagents are generating outputs; could be slow model / API throttle / overcomplicated query / etc. |

License

CC BY-NC-ND 4.0