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.
npx skills add iblai/medical-healthcare-agents --skill pubmedgit clone --depth 1 https://github.com/iblai/medical-healthcare-agentsWrote 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/skills/iblai/medical-healthcare-agents/pubmed)<a href="https://agentmods.dev/skills/iblai/medical-healthcare-agents/pubmed"><img src="https://agentmods.dev/badge/skills/iblai/medical-healthcare-agents/pubmed/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/skills/iblai/medical-healthcare-agents/pubmed"><img src="https://agentmods.dev/badge/skills/iblai/medical-healthcare-agents/pubmed.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 | $0.00037 | $0.00753 |
| Opus 5 | $0.00018 | $0.00377 |
| Sonnet 5 | $0.00007 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
pubmed 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 12d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PubMed / NCBI E-utilities
What it is
PubMed is the NLM/NCBI index of over 37 million biomedical citations including MEDLINE, life science journals, and online books. The NCBI E-utilities REST API provides programmatic access to search (ESearch), fetch (EFetch), and summarize (ESummary) records. Agents use it to retrieve primary literature evidence for clinical questions, PA appeal support, research synthesis, and evidence-based guideline summaries. An institutional API key raises rate limits significantly above the unauthenticated tier.
When to use this skill
- Search for clinical evidence supporting or refuting a treatment approach or drug use
- Retrieve abstracts and citation metadata for a set of PMIDs to feed into a systematic review workflow
- Find RCTs or meta-analyses relevant to a specific diagnosis, intervention, or outcome
- Support a prior authorization appeal by surfacing peer-reviewed literature on medical necessity
- Look up pharmacological or safety studies for a drug or device under evaluation
Credentials
This skill wraps a public API. Copy ~/.openclaw/.env.example to ~/.openclaw/.env and optionally set the following variable for increased rate limits:
PUBMED_BASE_URL- E-utilities base URL (https://eutils.ncbi.nlm.nih.gov/entrez/eutils)PUBMED_API_KEY- NCBI API key registered atncbi.nlm.nih.gov/account; raises rate limit to 10 requests/sec (vs. 3/sec unauthenticated) — optional but recommended for production
Key operations
GET /esearch.fcgi?db=pubmed&term={query}&retmax={n}— search PubMed and return list of PMIDsGET /efetch.fcgi?db=pubmed&id={pmids}&rettype=abstract&retmode=xml— fetch full abstracts in XML for a list of PMIDsGET /esummary.fcgi?db=pubmed&id={pmids}&retmode=json— lightweight citation metadata (title, authors, journal, year, DOI)GET /esearch.fcgi?db=pubmed&term={query}&datetype=pdat&mindate={YYYY}&maxdate={YYYY}— date-range-limited searchGET /esearch.fcgi?db=pubmed&term={query}+AND+meta-analysis[pt]— filter to publication type (meta-analysis, RCT, review)GET /elink.fcgi?dbfrom=pubmed&id={pmid}&cmd=prlinks— retrieve publisher full-text link for open-access articles
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.
- 12d ago First seen · 38 lines · 37 tokens per session scan A e22fd6e0dfad
pubmed is a skill published in the GitHub repository iblai/medical-healthcare-agents (10 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 753 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
arithmetic-evaluator
Evaluate arithmetic expressions and return numeric results. Use when a user asks an arithmetic question, requests calculation, or provides a math expression involving numbers, parentheses, and arithmetic operators.
foundations-network-science
Network-science primitives for graph systems, centrality, PageRank, communities, contagion, link prediction, and temporal networks. Use when analyzing graph structure.
research-scout
Mines academic papers, research blogs, and curator newsletters for stealable methods and frameworks. Use when scanning research for applicable techniques across AI/ML/SWE.
ai-scaling-laws
Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, tokens-per-parameter ratios, or over-training tradeoffs.
ai-ml-data-science
Builds ML, responsible-AI, and multimodal models. Use when doing data science or explaining fairness, privacy, speech, vision-language, or diffusion mechanics.
research-arxiv-scout
Discovers and triages recent arXiv papers for AI/ML, agents, and software/QA. Use when scouting categories, arXiv IDs, or source lists.