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/feed)<a href="https://agentmods.dev/commands/aipoch/medical-research-skills/feed"><img src="https://agentmods.dev/badge/commands/aipoch/medical-research-skills/feed/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/feed"><img src="https://agentmods.dev/badge/commands/aipoch/medical-research-skills/feed.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 | $0.00878 |
| Opus 5 | $0.00000 | $0.00439 |
| Sonnet 5 | $0.00000 | $0.00176 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
feed 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feed — Paper Recommendations
Execute all steps without asking for user confirmation at intermediate stages. Report results at the end.
Environment Detection
Read mode from config.json. If "auto":
- If
config.jsonis readable → Tier B/C - If bash is available → Tier C
- Otherwise → Tier A
Steps
1. Read Current Reading State
[Tier C / B] Read config.json to get data_dir (notes_dir = data_dir/notes). Read data_dir/notes/reading_list.md to understand:
- Papers already read (
[x]) and their topics - Papers downloaded but not yet read
[Tier A] Ask the user to paste their Session Card if not already present in this conversation.
2. Update search_config.json
Based on already-read paper topics and the research framework in MEMORY.md, update search_config.json:
tiers.tier1/2/3.terms— refresh search termslast_updated— today's datebased_on_notes— read paper note filenames, sliding window max 25 (drop oldest when full)update_reason— brief note on what drove this update
Search term principles (reference MEMORY.md for research direction):
- Tier 1: directly addresses the core research question
- Tier 2: same mechanism or method in a different disease context
- Tier 3: wild-card cross-domain inspiration, method-heavy
[Tier A] Update search terms in session memory; include updated terms in the session card output at the end.
3. Search Semantic Scholar
Read tiers.tier1/2/3.terms from search_config.json. For each search term, call:
GET https://api.semanticscholar.org/graph/v1/paper/search
?query={url-encoded term}
&fields=title,year,citationCount,journal,authors,externalIds,openAccessPdf,publicationVenue
&limit=5
Headers: x-api-key: {s2_api_key from config.json, if set}
Wait 3 seconds between queries. On a 429 response, wait 15 seconds and retry once.
[Tier C optimization] If Python is available, run python recommend.py instead of the WebFetch calls above.
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.
- 7d ago First seen · 115 lines · 0 tokens per session scan A c016746dec33
feed 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 878 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.
query-tcga
Query TCGA/GDC for projects, mutations, or clinical data. Use when the user asks for TCGA cohorts, mutation counts, or clinical variables from the Genomic Data Commons.
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.
fit-dose-response
Fit dose-response curves and compute IC50/AUC. Use when the user has viability data across drug concentrations, or asks about IC50, EC50, or drug sensitivity.
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.