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 skills add K-Dense-AI/drug-discovery-agent-skills --skill openfdagit clone --depth 1 https://github.com/K-Dense-AI/drug-discovery-agent-skillsWrote 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.
[](https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/openfda)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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 — 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.
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.
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.
- 12d ago First seen · 186 lines · 155 tokens per session scan A e118eb13f37e
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.
Other skills, from other repositories
patsnap-biological-modality
Biological sequence and modality intelligence via Patsnap MCP.
patsnap-chemical-molecular
Patsnap Chemical Molecular MCP for AI agents. Search 160M+ chemical structures, synthetic routes, and bioactivity data via specialized chemistry tools.
patsnap-scientific-translational-evidence
Patsnap Scientific & Translational Evidence MCP for AI agents. Retrieval platform focusing on scientific literature and translational outcomes, covering academic publication queries and translational medicine record tracking.
patsnap-target-disease
Patsnap Target & Disease MCP for AI agents. Target and disease profiling tool, covering target characterization, disease profiling, and epidemiology evidence retrieval.
patsnap-solution-engine
Patsnap TRIZ Concept Solution Engine MCP for AI agents. Generates innovation or product cost-reduction concepts through asynchronous TRIZ and TRIZ/DFMA workflows. Use for engineering problem solving, concept alternatives, cost-reduction analysis, task-progress retrieval, and selected-solution details.
patsnap-clinical-trials
Patsnap Clinical Trials MCP for AI agents. Intelligent clinical trial retrieval system, covering registered trial tracking, trial details and results analysis, and supporting clinical semantic search.