pubmed-search-agent: Instructions file for Claude Code

CLAUDE.md

pubmed-search-agent CLAUDE.md is an instructions file for Claude Code from Dariolex/pubmed-search-agent. It costs 3,580 tokens per session, scanned A, original, MIT.

Instructions for a search agent that turns ordinary-language questions into advanced PubMed searches. PubMed is a database of biomedical research, and the agent can use NCBI's official search APIs and rank results by meaning.

In plain words
What is it for?
Use it to find studies matching detailed medical questions, such as recent randomized trials on a condition while excluding case reports.
Why use it?
It helps people search medical research without knowing PubMed's field tags, Boolean operators, subject headings, date filters, and publication types.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Dariolex/pubmed-search-agent's own configuration. It tells Claude Code how to work on pubmed-search-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pubmed-search-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Dariolex/pubmed-search-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Dariolex/pubmed-search-agent/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Dariolex/pubmed-search-agent

Made for: Claude Code.

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 pubmed-search-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dariolex/pubmed-search-agent/claude-md/github.svg)](https://agentmods.dev/instructions/dariolex/pubmed-search-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dariolex/pubmed-search-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/dariolex/pubmed-search-agent/claude-md/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.

agentmods 80×15 button for pubmed-search-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dariolex/pubmed-search-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/dariolex/pubmed-search-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,580 This file is loaded in full into every session.
When invoked 3,580 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03580 $0.03580
Opus 5 $0.01790 $0.01790
Sonnet 5 $0.00716 $0.00716
Haiku 4.5 $0.00358 $0.00358

Measured 9d ago against content hash 8a178bb1a045, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pubmed-search-agent CLAUDE.md 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 9d 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.

CLAUDE.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PubMed NL Search Agent — CLAUDE.md

1. Obiettivo del progetto

Costruire un motore di ricerca che permetta di interrogare PubMed (via API E-utilities di NCBI) formulando query in linguaggio naturale, che vengono tradotte automaticamente nella sintassi di ricerca avanzata di PubMed (tag di campo, operatori booleani, filtri MeSH, date, ecc.), eseguite contro le API reali, e i cui risultati vengono poi filtrati per rilevanza semantica rispetto all'intento originale dell'utente — non per semplice matching di parole chiave.

Esempio di flusso:

Utente: "Trovami gli studi degli ultimi 3 anni su immunoterapia nel melanoma metastatico,
         solo trial clinici randomizzati, escludendo case report"
   ↓
Traduzione NL → query PubMed:
("melanoma"[MeSH Terms] OR "melanoma"[tiab]) AND
("immunotherapy"[MeSH Terms] OR "immunotherapy"[tiab]) AND
"metastatic"[tiab] AND
"randomized controlled trial"[pt] AND
("2023"[dp] : "2026"[dp])
NOT "case reports"[pt]
   ↓
Esecuzione su ESearch/EFetch (NCBI E-utilities, con api_key)
   ↓
Filtro di rilevanza semantica sui risultati (Claude)
   ↓
Output: elenco ordinato per pertinenza, con motivazione della rilevanza

2. Stato del progetto

  • API key NCBI già generata (E-utilities, non Datasets API — parametro api_key, non api-key).
  • Sviluppo previsto interamente in Claude Code (serve accesso di rete live verso eutils.ncbi.nlm.nih.gov per testare le chiamate reali, non disponibile in ambiente chat).
  • Questo file è il documento guida iniziale: va raffinato in modalità di pianificazione (plan mode) mano a mano che l'architettura si consolida.

3. Architettura

pubmed-search-agent/
├── CLAUDE.md
├── .env
├── .env.example
├── pytest.ini
├── requirements.txt
├── docs/superpowers/
│   ├── specs/                 # design approvati in brainstorming
│   └── plans/                 # piani di implementazione
├── src/
│   ├── pubmed_errors.py       # gerarchia di eccezioni condivisa
│   ├── pubmed_models.py       # dataclass + parsing XML puro (nessuna rete)
│   ├── pubmed_client.py       # wrapper E-utilities, rate limiting, retry
│   ├── run_search.py          # entry-point CLI: query -> esearch/efetch -> JSON
│   ├── nl_query_translator.py # NL → sintassi PubMed
│   ├── mesh_resolver.py       # termini liberi → MeSH controllati
│   └── mcp_server.py          # tool MCP `search_pubmed_papers`
├── tests/
│   ├── test_pubmed_errors.py
│   ├── test_pubmed_models.py
│   ├── test_pubmed_client.py
│   ├── test_pubmed_live.py
│   ├── test_nl_query_translator.py
│   ├── test_run_search.py
│   ├── record_fixtures.py     # registra risposte NCBI reali
│   └── fixtures/              # XML NCBI salvati, senza api_key
└── examples/
    └── sample_queries.md

Read the full file on GitHub · 223 lines

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. 9d ago First seen · 223 lines · 3,580 tokens per session scan A 8a178bb1a045

Subscribe to this mod's changes

pubmed-search-agent CLAUDE.md is an instructions file published in the GitHub repository Dariolex/pubmed-search-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 3,580 tokens to every session, about $0.0179 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens