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 agentmods add commands/usathyan/epistract/acquiregit clone --depth 1 https://github.com/usathyan/epistractWhat 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 | $0.00021 | $0.01046 |
| Opus 5 | $0.00010 | $0.00523 |
| Sonnet 5 | $0.00004 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
epistract-acquire 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 3d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epistract PubMed Acquisition
You are building a document corpus from PubMed for the epistract knowledge graph pipeline.
Usage Guard
If invoked with no arguments or with --help: Display the following usage block verbatim and stop — do not run any pipeline steps.
Usage: /epistract:acquire <query> [options]
Required:
<query> PubMed search query (standard PubMed syntax; enclose multi-word queries in quotes)
Options:
--max <n> Maximum articles to fetch (default: 20)
--output <dir> Output directory for downloaded corpus (default: ./epistract-corpus)
--full-text Attempt full-text fetch from PMC when available (default: true)
Examples:
/epistract:acquire "remdesivir COVID-19 clinical trial"
/epistract:acquire "KRAS inhibitor" --max 50
/epistract:acquire "sotorasib NSCLC" --max 100 --output ./kras-corpus
Prerequisites
Prerequisites
The PubMed connector must be available. If it is not connected, tell the user:
PubMed connector not found. Connect it in Claude settings (Settings > Connectors > PubMed) or in Claude Code:
/plugin marketplace add anthropics/life-sciences && /plugin install pubmed@life-sciences
Arguments
query(required): PubMed search query (supports standard PubMed syntax)--max(optional): Maximum articles to fetch (default: 20)--output(optional): Output directory (default: ./epistract-corpus)--full-text(optional): Attempt to fetch full text from PMC when available (default: true)
Pipeline Steps
Step 1: Search PubMed
Use the PubMed connector to search for articles matching the query. Respect NCBI rate limits — if you receive a rate limit message, wait briefly and retry.
Refine the query if needed for better results. For example, add date filters, MeSH terms, or journal restrictions based on the user's intent.
Step 2: Fetch Article Metadata
For each result, collect:
- PMID
- Title
- Authors (list)
- Journal name
- Publication year
- Abstract text
- MeSH terms (if available)
- DOI (if available)
- PMC ID (if available)
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.
- 3d ago First seen · 126 lines · 21 tokens per session scan A 33620c2c7450
epistract-acquire is a command published in the GitHub repository usathyan/epistract (8 stars, last pushed 18d ago), licensed MIT. It adds 21 tokens to every session and 1,046 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 2026-08-31.
Other commands, from other repositories
cross-validate
Take a specific scientific claim and confirm or refute it across 3+ independent databases, then report concordance. Use before publishing, citing, or acting on a fact when you want to know how strongly it's supported. Forces multi-source verification that the agent doesn't naturally enforce.
translate-id
Resolve an identifier across all relevant namespaces (HGNC symbol, Ensembl, UniProt, NCBI Gene ID, RefSeq, MGI, OMIM, ChEMBL, PubChem, etc.). Detects the input namespace automatically, picks the right resolver tool, and returns a complete cross-reference table. Use when you have an ID in one namespace and need it in…
flow-nexus-neural
Train and deploy neural networks in distributed sandboxes.
check-dev
Type-check a Z specification with fuzz.
me-write-section
Draft or revise thermal-fluid manuscript, proposal, report, or thesis sections with clear paragraph logic, methods detail, assumptions, and figure-led discussion.
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.