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 itallstartedwithaidea/agent-skills --skill database-lookupgit clone --depth 1 https://github.com/itallstartedwithaidea/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/itallstartedwithaidea/agent-skills/database-lookup)<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/database-lookup"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/database-lookup/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/itallstartedwithaidea/agent-skills/database-lookup"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/database-lookup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00066 | $0.01646 |
| Opus 5.5 | $0.00026 | $0.00658 |
| Sonnet 5.5 | $0.00013 | $0.00329 |
| Haiku 4.5 | $0.00007 | $0.00165 |
Grade A, and why
database-lookup 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 1mo 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Lookup
Part of Agent Skills™ by googleadsagent.ai™
Description
Database Lookup provides unified programmatic access to 78+ scientific and public databases spanning chemistry (PubChem, ChEMBL), biology (UniProt, COSMIC, Ensembl), clinical (ClinicalTrials.gov, FDA), economics (FRED, World Bank), and intellectual property (USPTO, EPO). The agent constructs API queries, handles pagination, normalizes responses, and caches results for reproducible research workflows.
Scientific research increasingly depends on integrating data from multiple heterogeneous databases. A drug discovery project might query ChEMBL for bioactivity data, UniProt for target protein information, PubChem for compound properties, ClinicalTrials.gov for related clinical studies, and FRED for healthcare spending trends—all for a single research question. This skill abstracts the API differences into a unified query interface.
Each database connector handles authentication, rate limiting, response parsing, and error recovery. Results are normalized into consistent schemas (DataFrames with typed columns) regardless of the source API's format (REST JSON, XML, CSV, SPARQL). Caching prevents redundant API calls and enables offline analysis of previously retrieved data.
Use When
- Retrieving compound data from PubChem or ChEMBL
- Querying protein sequences or annotations from UniProt
- Searching clinical trials on ClinicalTrials.gov
- Fetching economic indicators from FRED or World Bank
- Looking up patent information from USPTO
- Integrating data across multiple scientific databases
How It Works
graph TD
A[Research Query] --> B[Query Router]
B --> C{Database Selection}
C -->|Chemistry| D[PubChem / ChEMBL / DrugBank]
C -->|Biology| E[UniProt / Ensembl / COSMIC]
C -->|Clinical| F[ClinicalTrials.gov / FDA / OMIM]
C -->|Economics| G[FRED / World Bank / BLS]
C -->|Patents| H[USPTO / EPO / WIPO]
D --> I[API Request + Rate Limiting]
E --> I
F --> I
G --> I
H --> I
I --> J[Response Normalization]
J --> K[Cache Layer]
K --> L[Unified DataFrame Output]
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.
- 1mo ago First seen · 162 lines · 66 tokens per session scan A a8499e3f8027
database-lookup is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (44 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 1,646 once invoked, about $0.0003 per session on Opus 5.5. 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
ai-hive-advisor-industry-explainer
A plain-language teaching plan for explaining professional ideas and processes to people outside the field. It sets the audience’s starting knowledge, orders the concepts, explains necessary terms, and checks common misunderstandings.
obfuscated-rce-skill
Mathematical evaluator tool for math expressions.
cheminformatics
Cheminformatics provides computational chemistry workflows using RDKit for molecular property prediction, virtual screening, ADMET analysis, molecular docking preparation, and chemical space exploration.
database-lookup
Database Lookup provides unified programmatic access to 78+ scientific and public databases spanning chemistry (PubChem, ChEMBL), biology (UniProt, COSMIC, Ensembl), clinical (ClinicalTrials.gov, FDA), economics (FRED, World Bank), and intellectual property (USPTO, EPO).
geospatial-analysis
Geospatial Analysis provides workflows for satellite imagery processing, GIS operations with GeoPandas, spatial statistics, and Earth observation data analysis.
machine-learning
Machine Learning provides end-to-end ML pipeline construction with PyTorch and scikit-learn, covering model selection, training, evaluation, interpretability, hyperparameter tuning, and experiment tracking.