openfda

openfda is a skill for Claude Code from K-Dense-AI/drug-discovery-agent-skills. It costs 155 tokens per session (2,419 once invoked), scanned A, original, MIT.

A connection to openFDA, the FDA's public database of drug safety reports, approvals, labels, recalls, and shortages.

In plain words
What is it for?
Use it to search adverse-event reports, approval histories, official labels, recalls, and shortages, and to examine possible safety signals.
Why use it?
It helps check what regulators and post-market reports say about a drug or drug class after it has been used in people.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: built for openclaw.

Good fit Use it to search adverse-event reports, approval histories, official labels, recalls, and shortages, and to examine possible safety signals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/k-dense-ai/drug-discovery-agent-skills/openfda
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.

Any agent
npx skills add K-Dense-AI/drug-discovery-agent-skills --skill openfda
Clone the repo
git clone --depth 1 https://github.com/K-Dense-AI/drug-discovery-agent-skills

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 openfda

README.md
[![agentmods](https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/openfda/github.svg)](https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/openfda)
Your own site
<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/openfda"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/openfda/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 openfda

Your own site · 80×15
<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/openfda"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/openfda.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,419 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00155 $0.02419
Opus 5 $0.00077 $0.01210
Sonnet 5 $0.00031 $0.00484
Haiku 4.5 $0.00015 $0.00242

Measured 12d ago against content hash e118eb13f37e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

openfda 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/_common.py, scripts/fda_adverse.py, scripts/fda_approvals.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/openfda/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

openFDA

The FDA's own post-market record, served as a public REST API: 20.6 M adverse-event reports, every drug application since 1939, and the full text of approved labels. It answers the question that comes after the biology — what has already happened to this molecule, or to its class, in people — and it is the cheapest safety evidence available anywhere.

Base URL: https://api.fda.gov — REST, no key required. Docs: open.fda.gov/apis · field reference Checked against: the live API, August 2026; FAERS data current to 2026-07-30.

Read references/api-reference.md before writing a query by hand, references/endpoint-fields.md before trusting a field name, and references/disproportionality.md before reporting any signal — that one is judgement, not syntax.

The three scripts

Script Answers
fda_adverse.py What has been reported against this drug, and is any of it disproportionate?
fda_approvals.py When was it approved, by whom, and how many indications has it gained?
fda_labels.py What does the approved label actually say?

Zero results arrive as HTTP 404

This is the single thing to get right. A search that matches nothing returns:

HTTP 404  {"error": {"code": "NOT_FOUND", "message": "No matches found!"}}

That is a successful query with an empty result set. Any client that treats non-200 as failure turns "this drug has no reports" into a crash, and — worse — makes a typo indistinguishable from a real zero, because a misspelled field name also returns 404. get() in scripts/_common.py converts NOT_FOUND into an empty payload; when a count comes back empty, check the field name against references/endpoint-fields.md before believing it.

The other two surprises: limit above 1000 returns 403 API_KEY_MISSING (a key raises the daily quota, not the per-request cap — lower limit instead), and skip is hard-capped at 25000, so a search matching 500 000 reports has 25 000 reachable records. Partition by receivedate to go deeper.

Read the full file on GitHub · 186 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 186 lines · 155 tokens per session scan A e118eb13f37e

Subscribe to this mod's changes

openfda is a skill published in the GitHub repository K-Dense-AI/drug-discovery-agent-skills (28 stars, last pushed 5d ago), licensed MIT. It adds 155 tokens to every session and 2,419 once invoked, about $0.0008 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 2026-08-30.