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 kthorn/research-superpower --skill checking-chemblgit clone --depth 1 https://github.com/kthorn/research-superpowerWrote 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/kthorn/research-superpower/checking-chembl)<a href="https://agentmods.dev/skills/kthorn/research-superpower/checking-chembl"><img src="https://agentmods.dev/badge/skills/kthorn/research-superpower/checking-chembl.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.03602 |
| Opus 5 | $0.00013 | $0.01801 |
| Sonnet 5 | $0.00005 | $0.00720 |
| Haiku 4.5 | $0.00003 | $0.00360 |
Grade A, and why
Checking ChEMBL for Structured SAR Data scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://www.ebi.ac.uk/chembl/api/data/document.json?doi=DOI" How it starts
The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checking ChEMBL for Structured SAR Data
Overview
ChEMBL is a manually curated database of ~99,000 medicinal chemistry papers with extracted, standardized bioactivity data. If a paper is in ChEMBL, you can access structured data without parsing PDFs.
Core principle: Check ChEMBL first for medicinal chemistry papers. Curated data is more reliable than table parsing.
When to Use
Use this skill when:
- Paper describes medicinal chemistry / drug discovery
- Abstract mentions compound series, SAR, or activity data
- Paper has IC50, MIC, Ki, EC50, or other bioactivity measurements
- Before attempting to extract data from tables/figures
- Paper scored ≥ 7 in relevance evaluation
When NOT to use:
- Non-medicinal chemistry papers (cell biology, genomics, etc.)
- Papers without activity measurements
- Reviews without primary data
- Very recent papers (< 6 months, likely not curated yet)
ChEMBL API Basics
Base URL: https://www.ebi.ac.uk/chembl/api/data/
No authentication required
CRITICAL: ChEMBL can ONLY be queried by DOI, NOT by PMID
- The API returns PMID in results, but does not accept it as a query parameter
- Always use DOI for lookups:
?doi=10.1234/example - PMID queries will return 0 results even if paper exists in ChEMBL
Two-step process:
- Check if paper (by DOI) is in ChEMBL
- If yes, retrieve bioactivity data
Step 1: Check if Paper in ChEMBL
Query by DOI (ONLY method that works):
curl -s "https://www.ebi.ac.uk/chembl/api/data/document.json?doi=DOI"
⚠️ IMPORTANT: Must use DOI, not PMID
# ✅ CORRECT - Use DOI
doi="10.1021/jm401507s"
curl -s "https://www.ebi.ac.uk/chembl/api/data/document.json?doi=$doi"
# ❌ WRONG - PMID won't work (will return 0 results)
pmid="24446688"
curl -s "https://www.ebi.ac.uk/chembl/api/data/document.json?pubmed_id=$pmid" # Does NOT work!
If you only have PMID: Fetch DOI from PubMed first, then query ChEMBL with the DOI.
Response structure:
{
"documents": [
{
"document_chembl_id": "CHEMBL3120156",
"doi": "10.1021/jm401507s",
"title": "Discovery and development of simeprevir (TMC435), a HCV NS3/4A protease inhibitor.",
"abstract": "Hepatitis C virus is a blood-borne infection...",
"pubmed_id": 24446688,
"journal": "J Med Chem",
"year": 2014,
"doc_type": "PUBLICATION"
}
],
"page_meta": {
"total_count": 1
}
}
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.
- 8d ago First seen · 404 lines · 26 tokens per session scan A b9ed59576f31
Checking ChEMBL for Structured SAR Data is a skill published in the GitHub repository kthorn/research-superpower (123 stars, last pushed 10mo ago), licensed MIT. It adds 26 tokens to every session and 3,602 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…