Medical Research Agent Skills is a library of agent instructions for medical and biomedical research, covering evidence analysis, study protocol design, data analysis, and academic writing. Researchers use it to guide compatible coding agents through common scientific workflows. The catalogue contains many of the library's skills and commands.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aipoch/medical-research-skillsnpx agentmods add commands/aipoch/medical-research-skills/setupWrote 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.
[](https://agentmods.dev/commands/aipoch/medical-research-skills/setup)<a href="https://agentmods.dev/commands/aipoch/medical-research-skills/setup"><img src="https://agentmods.dev/badge/commands/aipoch/medical-research-skills/setup/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.
<a href="https://agentmods.dev/commands/aipoch/medical-research-skills/setup"><img src="https://agentmods.dev/badge/commands/aipoch/medical-research-skills/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01337 |
| Opus 5 | $0.00000 | $0.00668 |
| Sonnet 5 | $0.00000 | $0.00267 |
| Haiku 4.5 | $0.00000 | $0.00134 |
Grade A, and why
setup 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup — Initial Configuration
Run this on first use. Configures the environment automatically and collects your research profile through a guided conversation.
Steps
0. Auto Environment Initialization
Detect the current capability tier before doing anything else.
If Tier C (bash available):
- Check whether
.claude/commandsexists. If not, run:mkdir -p .claude && ln -s ../commands .claude/commands - Check whether
.claude/settings.local.jsonexists. If not, run:cp settings.local.json .claude/settings.local.json - Inform the user: "Environment configured automatically — no manual steps needed."
If Tier B (file system, no bash):
- Inform the user of the minimum permissions needed: file read/write access to this directory and
data_dir. - Proceed to the questionnaire.
If Tier A (Web Claude, no file system):
- Skip file initialization.
- At the end of setup, generate a Session Card from
SESSION_CARD_TEMPLATE.mdfilled with the user's answers. - Explain: "Since there is no file system here, I will use a Session Card to maintain your research context across conversations. Save the card I generate at the end and paste it at the start of each new session."
1. Confirm data_dir is Configured
Tier C / B: Check whether config.json exists and data_dir is filled in (not a placeholder). If missing:
Please edit
config.jsonand setdata_dirto the folder where you keep your research PDFs, then run/setupagain.
Tier A: Ask the user directly:
Where do you usually save your research papers? (Just describe it — folder name, cloud drive, etc. For context only.)
2. Research Profile Questionnaire
Ask one question at a time. Wait for each answer before proceeding.
Q1 — What disease or clinical problem are you researching?
Describe your core research focus. Examples:
- Disease name: glioma, type 2 diabetes, acute myocardial infarction, Alzheimer's disease
- Pathological mechanism: ferroptosis, immune evasion, drug resistance, metabolic reprogramming
- Clinical problem: post-surgical recurrence prediction, treatment response biomarkers, survival prognosis modeling
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.
- 6d ago First seen · 143 lines · 0 tokens per session scan A 8c08956963bf
setup is a command published in the GitHub repository aipoch/medical-research-skills (1,848 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,337 tokens. 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 2026-09-03.
Other commands, from other repositories
run-gsea
Pathway enrichment on a ranked gene list (GSEA or ORA). Use when the user asks which pathways are enriched, wants GSEA/fgsea, or has DE results to interpret biologically.
analyze-degs
Differential expression from a count matrix with DESeq2. Use when the user has bulk RNA-seq counts and wants DEGs, a volcano plot, or asks which genes differ between conditions.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.