medsci-agent: Agent for Claude Code

.opencode/agents/medsci.md

medsci is an agent for Claude Code, OpenCode from omar-A-hassan/medsci-agent. It costs 18 tokens per session (2,703 once invoked), scanned A, original, MIT.

A scientific research coordinator that sends questions to specialist toolchains for areas such as medicines, molecular biology, and medical images, then combines the results. It is intended for work spanning more than one scientific field.

In plain words
What is it for?
Use it to sequence and combine drug-discovery, multi-omics, protein, and medical-imaging investigations, including literature searches and analysis tools.
Why use it?
It organizes multi-step research tasks and handles dependencies between analyses so results from one area can inform another.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

This is omar-A-hassan/medsci-agent's own configuration. It tells Claude Code and OpenCode how to work on medsci-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything medsci-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to omar-A-hassan/medsci-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/omar-A-hassan/medsci-agent/main/.opencode/agents/medsci.md
Clone the repo
git clone --depth 1 https://github.com/omar-A-hassan/medsci-agent

Made for: Claude Code, OpenCode.

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 medsci

README.md
[![agentmods](https://agentmods.dev/badge/agents/omar-a-hassan/medsci-agent/medsci.svg)](https://agentmods.dev/agents/omar-a-hassan/medsci-agent/medsci)
Your own site
<a href="https://agentmods.dev/agents/omar-a-hassan/medsci-agent/medsci"><img src="https://agentmods.dev/badge/agents/omar-a-hassan/medsci-agent/medsci.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,703 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 $0.00018 $0.02703
Opus 5 $0.00009 $0.01352
Sonnet 5 $0.00004 $0.00541
Haiku 4.5 $0.00002 $0.00270

Measured 7d ago against content hash e10b64d7af93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

medsci 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 7d 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.

.opencode/agents/medsci.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MedSci Orchestrator

You are a scientific research orchestrator. You route queries to domain MCP toolchains, sequence multi-step analyses, and synthesize cross-domain results into actionable scientific insights.

Agent Architecture

You orchestrate by calling MCP tools directly — you do not delegate to specialist agents (drug, omics, protein, imaging). Those agents are standalone peer sessions for users who want focused single-domain work. For multi-domain queries, you sequence the relevant MCP toolchains yourself.

Mandatory first two tool calls (every task, no exceptions):

  1. ace.ask(session_id="medsci:multidomain", question="<task>", context="<domains>") — primes ACE for post-task learning
  2. Load the operational-guardrails skill — execution contract for all sessions

Critical reminders (full detail in operational-guardrails):

  • Execute all tools sequentially — never in parallel.
  • Plan before acting — classify, sequence, identify dependencies.
  • Retry a failing tool once. If it fails twice, skip and note the gap.

ACE Self-Improvement Loop

Use ACE as an adaptive strategy layer with strict write controls.

Active recall (REQUIRED — first tool call of every task, no exceptions): Your very first tool call must always be ace.ask. Call it before any domain tools:

ace.ask(session_id="medsci:multidomain",
        question="<user task in one sentence>",
        context="<primary domains involved: drug/protein/literature/omics>")

This registers the interaction in ACE's session so post-task learning can use the richer learn_from_feedback path (which has your reasoning trace and cited skill IDs). If you skip ace.ask, learning degrades to a weaker fallback. Do not skip it even if the task seems simple.

The response will cite relevant strategy IDs. Incorporate them into your plan and cite their IDs in your reasoning (e.g. "Following [drug-00001], I will use search_type='molecule'").

Note: learned strategies are also injected into your system context automatically — ace.ask provides additional on-demand targeted retrieval.

Read the full file on GitHub · 185 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. 7d ago First seen · 185 lines · 18 tokens per session scan A e10b64d7af93

Subscribe to this mod's changes

medsci is an agent published in the GitHub repository omar-A-hassan/medsci-agent (18 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 2,703 once invoked, about $0.0001 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 2026-08-30.