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 oligonucleotidesgit 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/oligonucleotides)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/oligonucleotides"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/oligonucleotides/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/oligonucleotides"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/oligonucleotides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00167 | $0.02044 |
| Opus 5 | $0.00084 | $0.01022 |
| Sonnet 5 | $0.00033 | $0.00409 |
| Haiku 4.5 | $0.00017 | $0.00204 |
Grade A, and why
oligonucleotides 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.
Oligonucleotide Therapeutics
The modality that sidesteps the protein entirely. If a target has no druggable pocket, no extracellular epitope, and no ligandable cysteine, an siRNA or antisense oligonucleotide can still silence its transcript — and the design is sequence arithmetic rather than chemistry intuition.
No installation, no network, no key. Sequence tiling, nearest-neighbour thermodynamics, and seed scanning are implemented in the standard library. Transcriptome-wide off-target scanning needs a FASTA that you supply. Thermodynamics: SantaLucia (1998) unified nearest-neighbour parameters.
Read references/sirna-and-aso-design.md before choosing a site, references/chemical-modifications.md before drawing a pattern, and references/delivery-and-safety.md before committing to the modality — that one is judgement, not syntax, and it is where programmes fail.
The three scripts
| Script | Answers |
|---|---|
oligo_design.py |
Which sites, and are their thermodynamics right? |
offtarget_scan.py |
What else will this silence? |
chemistry_plan.py |
What modifications, and where? |
Two mechanisms, two incompatible rule sets
siRNA loads into Argonaute-2 and is cleaved by RISC in the cytoplasm — it needs an RNA-like duplex throughout. Gapmer ASO recruits RNase H1, works in the nucleus, and needs an unmodified DNA core.
Two consequences. ASOs can target introns and pre-mRNA; siRNA cannot, because RISC only sees mature mRNA. And the chemistry is not interchangeable: a DNA gap in an siRNA breaks Argonaute loading, while fully modifying an ASO silently removes RNase H recruitment — the molecule binds its target beautifully and does nothing.
Duplex asymmetry decides which strand is loaded
The siRNA rule that matters most. RISC keeps the strand whose 5' end is less thermodynamically stable. Get it backwards and RISC loads the sense strand, silences something else, and your molecule looks simply inactive — sending you to hunt for delivery problems that do not exist.
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.
- 12d ago First seen · 156 lines · 167 tokens per session scan A 28e94b56a890
oligonucleotides 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 167 tokens to every session and 2,044 once invoked, about $0.0008 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.