research

research is a command for coding agents from mims-harvard/ToolUniverse. It costs 99 tokens per session (1,198 once invoked), scanned A, original, Apache-2.0.

A chat-based workflow for investigating scientific questions across multiple research databases. It checks specific claims against available sources and can report when the evidence is inconclusive.

In plain words
What is it for?
Use it to research a question, compare evidence from independent databases, analyse scientific data files, and identify claims that need more evidence.
Why use it?
It reduces guesswork when looking up published findings, database records, drug approvals, genetic variants, or similar scientific details.

Command

Part of the tooluniverse plugin — 140 skills, 8 commands, 1 agent, 1 hook, 1 MCP server shipped together

About the project

ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.

mims-harvard/ToolUniverse · 1,672 stars · on GitHub

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 commands/mims-harvard/tooluniverse/research
Clone the repo
git clone --depth 1 https://github.com/mims-harvard/ToolUniverse

Or install tooluniverse, the plugin that ships this one along with the rest of its 140 skills, 8 commands, 1 agent, 1 hook, 1 MCP server.

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 research

README.md
[![agentmods](https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/research.svg)](https://agentmods.dev/commands/mims-harvard/tooluniverse/research)
Your own site
<a href="https://agentmods.dev/commands/mims-harvard/tooluniverse/research"><img src="https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00099 $0.01198
Opus 5 $0.00049 $0.00599
Sonnet 5 $0.00020 $0.00240
Haiku 4.5 $0.00010 $0.00120

Measured 5d ago against content hash bce519e16140, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

2. **Execute**: call tools or skills directly. For batches of 5+ similar queries, use the Python SDK pattern (see below) — `subprocess.run(["tu", "run", ...])` per call reloads the registry every time.
plugin/commands/research.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research the following using ToolUniverse: $ARGUMENTS

Operating Rules

  1. Look up specific claims; don't guess them. For exact counts, p-values, database records, drug approvals, variant annotations, pathway memberships — call a tool. Memory is only for textbook-level background.

  2. Don't search for tools you already have. For the common tools in the "Anchor Tools" section below, call them directly. For anything else, run find_tools("topic") once, then get_tool_info(name) once. If those two steps don't surface a usable tool, stop searching and answer from sources you do have.

  3. Cross-validate high-stakes facts. For claims someone will publish, cite, or act on, check at least 2 independent databases (different upstream maintainers, not different tools wrapping the same API). State agreement or disagreement explicitly.

  4. An honest "INDETERMINATE" beats a confident wrong answer. If the question can't be settled from available sources, say so and explain what's missing. Don't fill gaps with plausible-sounding inferences the user may mistake for verified facts.

  5. For data-file analysis (CSV, TSV, h5ad, VCF, FASTA, tree files, etc.), route to the matching ToolUniverse skill before writing code:

    Skill('tooluniverse')   # loads the router, which dispatches to the specialized skill
    

    The skills encode discovered analysis conventions (which library, which filter, which denominator) that ad-hoc code often gets wrong. Do not re-derive conventions inside this chat.

Workflow

  1. Plan: state which tools or skills you'll need before calling them.
  2. Execute: call tools or skills directly. For batches of 5+ similar queries, use the Python SDK pattern (see below) — subprocess.run(["tu", "run", ...]) per call reloads the registry every time.
  3. Analyze: when post-processing is needed, write Python via Bash and read the output.
  4. Validate: cross-check key findings against a second source.
  5. Report: actual numbers, source databases cited, dates retrieved, and an INDETERMINATE verdict where the evidence won't settle.

Read the full file on GitHub · 76 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 · 76 lines · 99 tokens per session scan A bce519e16140

Subscribe to this mod's changes

research is a command published in the GitHub repository mims-harvard/ToolUniverse (1,672 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 1,198 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.