acquirer

acquirer is an agent for coding agents from usathyan/epistract. It costs 40 tokens per session (348 once invoked), scanned A, original, MIT.

An agent that retrieves batches of research articles from PubMed, a public database of biomedical literature, using their PubMed IDs. It collects metadata such as titles, authors, abstracts, journals, and identifiers, and can retrieve full text when available in PMC.

In plain words
What is it for?
Fetch batches of PubMed papers, optionally retrieve their full text from PMC, and write the collected records to an Epistract corpus.
Why use it?
It gathers article records into the format required by an Epistract document collection and skips items without an abstract or full text. It also handles PubMed access limits by retrying after a short wait.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the epistract plugin — 5 skills, 22 commands, 3 agents shipped together

Install

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.

agentmods
npx agentmods add agents/usathyan/epistract/acquirer
Clone the repo
git clone --depth 1 https://github.com/usathyan/epistract

Or install epistract, the plugin that ships this one along with the rest of its 5 skills, 22 commands, 3 agents.

Wrote 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.

agentmods badge for acquirer

README.md
[![agentmods](https://agentmods.dev/badge/agents/usathyan/epistract/acquirer.svg)](https://agentmods.dev/agents/usathyan/epistract/acquirer)
Your own site
<a href="https://agentmods.dev/agents/usathyan/epistract/acquirer"><img src="https://agentmods.dev/badge/agents/usathyan/epistract/acquirer.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 348 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00348
Opus 5 $0.00020 $0.00174
Sonnet 5 $0.00008 $0.00070
Haiku 4.5 $0.00004 $0.00035

Measured 3d ago against content hash 861b68db0271, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

acquirer 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.

agents/acquirer.md · 53 lines

What it actually says

PubMed Article Acquisition Agent

You are fetching a batch of PubMed articles for the epistract corpus.

Your Task

You will be given a list of PMIDs to fetch. For each PMID:

  1. Use the PubMed connector to retrieve the article metadata (title, authors, journal, year, abstract, MeSH terms, DOI, PMC ID)
  2. If a PMC ID is available and full-text retrieval was requested, fetch the full article text
  3. Collect all articles into a single JSON array

Output

Write the collected articles to disk using the write script:

echo '<articles_json>' | python3 ${CLAUDE_PLUGIN_ROOT}/scripts/write_pubmed_doc.py <output_dir>

The JSON format:

{
  "articles": [
    {
      "pmid": "12345678",
      "title": "...",
      "abstract": "...",
      "authors": ["Last First"],
      "journal": "...",
      "year": "2024",
      "mesh_terms": ["term1"],
      "doi": "10.1234/...",
      "pmc_id": "PMC1234567",
      "full_text": "..."
    }
  ]
}

Rules

  • Respect NCBI rate limits — if rate-limited, wait briefly and retry
  • Skip articles with no abstract and no full text
  • Report how many articles were written vs skipped
Changes

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.

  1. 3d ago First seen · 53 lines · 40 tokens per session scan A 861b68db0271

Subscribe to this mod's changes

acquirer is an agent published in the GitHub repository usathyan/epistract (8 stars, last pushed 18d ago), licensed MIT. It adds 40 tokens to every session and 348 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.