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
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.
git clone --depth 1 https://github.com/aipoch/medical-research-skillsWrote 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/discuss)<a href="https://agentmods.dev/commands/aipoch/medical-research-skills/discuss"><img src="https://agentmods.dev/badge/commands/aipoch/medical-research-skills/discuss/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/discuss"><img src="https://agentmods.dev/badge/commands/aipoch/medical-research-skills/discuss.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 | $0.00761 |
| Opus 5 | $0.00000 | $0.00380 |
| Sonnet 5 | $0.00000 | $0.00152 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
discuss 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 8d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/discuss — Paper Discussion
Deep Q&A on a paper already analyzed. Actively records valuable insights to the note file during the discussion, without waiting for the user to prompt it.
Steps
1. Locate the Note File
[Tier C / B] Read config.json to get data_dir (notes_dir = data_dir/notes).
The user can specify the paper by:
- Filename keyword (e.g.,
Dong_2023) - Author surname (e.g.,
Dong 2023) - Title keywords
Recursively search notes_dir/ for matching .md files. Read the matching note in full. If a same-named PDF exists, read it as well for supplementary detail.
If no match is found, inform the user and ask whether they want to provide the path directly or run /read first.
[Tier A] Ask the user to paste the note content from a previous session, or describe which paper they want to discuss.
2. Enter Discussion
Briefly recap the paper's core content in 2–3 sentences. Ask what the user wants to discuss.
In the note file, create a discussion log section (or use the existing one for today if it already exists):
## Discussion Log
### YYYY-MM-DD
3. Auto-Recording Rules During Discussion
Record immediately when any of the following occurs — no user prompt needed:
- The user asks a substantive question and receives a meaningful answer
- The discussion yields a new analytical angle or insight relevant to the user's own research
- A concept's scope or applicability is clarified in a way that matters for the research direction
- The user provides affirmative feedback ("that's useful", "this is exactly what I needed", etc.)
Do not record:
- Short clarification exchanges ("You mean...?" / "Yes")
- Off-topic chat unrelated to the paper or research
Quantity limit: If a single session generates more than 5 records, consolidate related entries rather than appending indefinitely.
Format:
### YYYY-MM-DD
**Q: [core of user's question, one sentence]**
[Answer in 3–5 sentences, preserving key terms and conclusions. If there is a specific implication for the user's own paper, add a separate line:]
→ Implication for your paper: ...
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.
- 8d ago First seen · 92 lines · 0 tokens per session scan A f967f353f52f
discuss is a command published in the GitHub repository aipoch/medical-research-skills (1,855 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 761 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.