Querying Openfda Labels

What it does

When your agent uses it

• The user wants the prescribing information for a drug
• Its boxed warning
• Approved indications
• Dosage forms and routes

Example prompts

• “Use the querying-openfda-labels skill to look up FDA drug labels, NDC directory entries, indications, boxed warnings, and recalls/enforcement…”
• “/querying-openfda-labels”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Normalize the drug name first. Use openmed.analyze_text to get the span,
2. 2Query /drug/label with openfda.generic_name:"" (or
3. 3Query /drug/ndc for package-level codes, dosage form, and route.
4. 4Query /drug/enforcement filtered to status:"Ongoing" to surface open
5. 5Cache results — labels change rarely; you do not need to re-query per note.
6. 6Attach the facts to the extracted drug keyed by RxCUI/NDC for traceability.

What it can do on your machine

Read from SKILL.md and the folder at commit 9dca507. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.fda.gov

  Also links to:

  • open.fda.gov
  • fda.gov
  • dailymed.nlm.nih.gov

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Querying Openfda Labels loads about 1.9k tokens when it runs. Until then it costs about 210 tokens; SKILL.md has 626 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~210

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from maziyarpanahi/openmed at commit 9dca507, republished under its Apache-2.0 licence (© maziyarpanahi). 626 words, ~1,872 tokens.

name

querying-openfda-labels

description

Looks up FDA drug labels, NDC directory entries, indications, boxed warnings, and recalls/enforcement actions via the free public OpenFDA API to enrich drugs that OpenMed extracts. Use when the user wants the prescribing information for a drug, its boxed warning, approved indications, dosage forms and routes, package NDC codes, RxCUI, or whether a product has an open recall. Trigger keywords: OpenFDA, drug label, SPL, prescribing information, boxed warning, black box warning, indications, NDC, package code, recall, enforcement, Class I recall, drug enrichment. Pairs adjacent to OpenMed NER: take a drug name (or RxNorm RxCUI) from openmed.analyze_text and resolve its label, NDC, and recall status. OpenFDA is public and free — no license barrier; send only de-identified drug names, never raw clinical notes.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

safety-pharmacovigilance

metadata.pairs

adjacent

metadata.version

1.0

import requests

def openfda(endpoint: str, search: str, limit: int = 1) -> list[dict]:
    url = f"https://api.fda.gov/drug/{endpoint}.json"
    r = requests.get(url, params={"search": search, "limit": limit}, timeout=30)
    if r.status_code == 404:        # OpenFDA returns 404 for zero matches
        return []
    r.raise_for_status()
    return r.json().get("results", [])

# 1) Label: boxed warning + indications for a generic drug.
label = openfda("label", 'openfda.generic_name:"warfarin"')
if label:
    rec = label[0]
    print("Boxed warning:", rec.get("boxed_warning", ["(none)"])[0][:200])
    print("Indication:", rec.get("indications_and_usage", ["(none)"])[0][:200])
    print("RxCUI:", rec.get("openfda", {}).get("rxcui"))

# 2) NDC: package codes, form, route.
ndc = openfda("ndc", 'generic_name:"warfarin"', limit=5)
for rec in ndc:
    print(rec["product_ndc"], rec.get("dosage_form"), rec.get("route"))

# 3) Enforcement: open recalls for a product.
recalls = openfda("enforcement",
                  'product_description:"warfarin"+AND+status:"Ongoing"', limit=5)
for rec in recalls:
    print(rec["classification"], "-", rec["reason_for_recall"][:120])

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/querying-openfda-labels of maziyarpanahi/openmed.

Open the folder on GitHubat commit 9dca507