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 generative-designgit 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/generative-design)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/generative-design"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/generative-design/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/generative-design"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/generative-design.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 | $0.00125 | $0.01835 |
| Opus 5 | $0.00063 | $0.00918 |
| Sonnet 5 | $0.00025 | $0.00367 |
| Haiku 4.5 | $0.00013 | $0.00184 |
Grade A, and why
generative-design 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generative Molecular Design
The Design half of design-make-test-analyse. REINVENT 4 turns a scoring function into molecules — de novo, or by decorating a scaffold, linking two fragments, or transforming a known active. It is the most capable open-source generative framework in medicinal chemistry, and it will optimise exactly what you ask for, including the parts you did not mean.
Tool: REINVENT 4 v4.8, Apache-2.0.
Not on PyPI — git clone and pip install -e .. Priors ship with the repository. An NVIDIA
GPU is effectively required for reinforcement learning.
Checked against: v4.8, June 2026.
Read references/reinvent-configuration.md before writing a run file, references/scoring-functions.md before defining an objective, and references/evaluating-generated-molecules.md before believing the output — that one is judgement, not syntax.
The three scripts
| Script | Answers |
|---|---|
reinvent_config.py |
Which generator, which prior, and what does the run file look like? |
scoring_profile.py |
What am I actually asking the model to optimise? |
parse_run.py |
Did the run produce distinct, useful molecules — or one scaffold a thousand times? |
The scoring function is the experiment
The model does not know what you meant. Everything it produces is a literal consequence of the objective, and unbounded rewards get exploited without exception:
| Reward | What the agent returns |
|---|---|
| logP, unbounded | long greasy alkyl chains |
| molecular weight upward | 900 Da molecules that satisfy nothing else |
| similarity to one reference | the reference, regenerated forever |
| a docking score | molecules exploiting that scoring function's blind spots |
So every numeric component gets a window, not a direction. Most properties have a desirable
range — molecular weight should be 250–500, not "as low as possible" — which is what
double_sigmoid is for. A reverse_sigmoid on molecular weight optimises toward methane.
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 · 163 lines · 125 tokens per session scan A 2c4597517285
generative-design is a skill published in the GitHub repository K-Dense-AI/drug-discovery-agent-skills (28 stars, last pushed 4d ago), licensed MIT. It adds 125 tokens to every session and 1,835 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-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.
patsnap-current-awareness
Patsnap Current Awareness MCP for AI agents. Tracking system for pharmaceutical industry dynamics and cutting-edge news, covering global medical news search and in-depth news detail mining.