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 chemical-spacegit 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/chemical-space)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/chemical-space"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/chemical-space/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/chemical-space"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/chemical-space.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 | $0.00126 | $0.02001 |
| Opus 5 | $0.00063 | $0.01001 |
| Sonnet 5 | $0.00025 | $0.00400 |
| Haiku 4.5 | $0.00013 | $0.00200 |
Grade A, and why
chemical-space 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purchasable Chemical Space
Make-on-demand catalogues turned virtual screening from "the million compounds we own" into "the tens of billions a vendor will synthesise". ZINC-22 holds about 54.9 billion 2D structures drawn from Enamine, WuXi, and Mcule; Enamine REAL Space defines around 94 billion combinatorially. This skill is about finding compounds in that space that can actually be ordered — and knowing when the space is too large to enumerate at all.
Services: https://cartblanche.docking.org (per-substance JSON) ·
https://files.docking.org/zinc22 (bulk tranche tree). Both unauthenticated.
Checked against: the live services, August 2026.
Read references/zinc22-and-cartblanche.md before calling the API or downloading a tranche, references/combinatorial-spaces.md before assuming a space can be enumerated, and references/screening-strategy.md before designing a cascade — that one is judgement, not syntax.
The two scripts
| Script | Answers |
|---|---|
cartblanche_lookup.py |
What is this ZINC id, and can I buy it? |
space_plan.py |
Which tranches do I need, and what will the screen cost? |
The API lies about its own responses
This is the thing to get right. CartBlanche answers unknown routes with HTTP 200, a
Content-Type: application/json header, and its React app's HTML:
| Route | Status | Content-Type | Body |
|---|---|---|---|
/substance/ZINC000000000053.json |
200 | application/json | JSON |
/substance.json?zinc_id=… |
200 | application/json | HTML shell |
/tranches.json |
200 | application/json | HTML shell |
Neither the status code nor the header can be trusted; only the body can. get_json() raises a
named error when a response begins with <. The one reliable JSON route is
/substance/<ZINC id>.json — treat CartBlanche as per-identifier lookup and use the file tree
for anything bulk.
What ships with it
6 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 · 156 lines · 126 tokens per session scan A 57440d5749ab
chemical-space 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 126 tokens to every session and 2,001 once invoked, about $0.0006 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.