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 chemblgit 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/chembl)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/chembl"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/chembl/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/chembl"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/chembl.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 | $0.00134 | $0.02480 |
| Opus 5 | $0.00067 | $0.01240 |
| Sonnet 5 | $0.00027 | $0.00496 |
| Haiku 4.5 | $0.00013 | $0.00248 |
Grade A, and why
chembl 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 13d 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.
the wrong molecule. The script encodes for you; a hand-written `curl` will not. How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChEMBL
ChEMBL is the curated database of measured bioactivity from the medicinal-chemistry literature — about 24.5 million activity values over 2.9 million compounds and 18,500 targets. It is where you find out what has already been made against a target, how potent it was, and how much of that is trustworthy.
Base URL: https://www.ebi.ac.uk/chembl/api/data — REST, no key.
Docs: interactive schema ·
ChEMBL home
Checked against: ChEMBL_37, released 2026-05-01.
Read references/api-reference.md before writing a request by hand, references/data-curation.md before modelling anything you pull, and references/entity-fields.md when you need to know what a field means or what type it really is.
The one thing to get right
Raw ChEMBL rows are not a dataset. activity.json?target_chembl_id=CHEMBL203 returns everything
ever published against that id: censored > values, rows ChEMBL itself flags as wrong, assays
whose target assignment is a guess, mutant-protein assays, and the same compound measured eight
times across four papers. Modelling that directly is the most common way to produce a QSAR model
that scores well and predicts nothing.
target_activities.py applies the curation and prints the attrition:
python skills/chembl/scripts/target_activities.py --uniprot P00533 \
--standard-type Ki --min-confidence 8 --out egfr_ki.tsv
# resolved P00533 -> CHEMBL203 (Epidermal growth factor receptor, SINGLE PROTEIN); 15 other ChEMBL target(s) share this component
# CHEMBL203 Ki assay_type=B: 538 activity rows
# fetching confidence scores for 78 assays
# input rows: 538
# dropped 23: potential_duplicate flag
# kept rows: 515
# warning: 78 molecule(s) have replicate pChEMBL values spanning >= 1.0 log units -- review before modelling
# wrote 321 rows to egfr_ki.tsv
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.
- 13d ago First seen · 172 lines · 134 tokens per session scan A 9f48130f57f5
chembl 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 134 tokens to every session and 2,480 once invoked, about $0.0007 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
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.