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 primekggit 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/primekg)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/primekg"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/primekg/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/primekg"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/primekg.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 | $0.00121 | $0.01880 |
| Opus 5.5 | $0.00048 | $0.00752 |
| Sonnet 5.5 | $0.00024 | $0.00376 |
| Haiku 4.5 | $0.00012 | $0.00188 |
Grade A, and why
primekg 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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PrimeKG Knowledge Graph Skill
Overview
PrimeKG is a precision medicine knowledge graph that integrates 20 high-quality primary resources into a single edge list. It describes 17,080 diseases with 4,050,249 relationships across ten major biological scales — drug-target, disease-gene, phenotype-disease, pathway and anatomical associations among them — over roughly 129,000 nodes.
Its distinguishing feature is drug-disease coverage: PrimeKG carries indication, contraindication, and off-label use edges that most disease knowledge graphs lack, which is what makes repurposing questions answerable here rather than merely askable.
Cite: Chandak P, Huang K, Zitnik M. Building a knowledge graph to enable precision medicine. Sci Data 10, 67 (2023). PMID 36732524.
Key capabilities:
- Search for nodes (genes, proteins, drugs, diseases, phenotypes)
- Retrieve direct neighbors (associated entities and clinical evidence)
- Analyze local disease context (related genes, drugs, phenotypes)
- Identify drug-disease paths (potential repurposing opportunities)
Data access: scripts/query_primekg.py reads kg.csv from the path in the PRIMEKG_DATA
environment variable (default data/PrimeKG/kg.csv). Download the CSV first — see
Data Path. The script works as a CLI or as an importable module:
python skills/primekg/scripts/query_primekg.py search Alzheimer --node-type disease
python skills/primekg/scripts/query_primekg.py neighbors EFO_0000249 --relation disease_protein
python skills/primekg/scripts/query_primekg.py context "Alzheimer's disease"
python skills/primekg/scripts/query_primekg.py paths CHEMBL1 D001 --max-depth 2
Add --format json for machine-readable output, or --data /path/to/kg.csv to override
PRIMEKG_DATA for one run. Every subcommand exits non-zero when the data file is missing.
When to Use This Skill
This skill should be used when:
- Knowledge-based drug discovery: Identifying targets and mechanisms for diseases.
- Drug repurposing: Finding existing drugs that might have evidence for new indications.
- Phenotype analysis: Understanding how symptoms/phenotypes relate to diseases and genes.
- Multiscale biology: Bridging the gap between molecular targets (genes) and clinical outcomes (diseases).
- Network pharmacology: Investigating the broader network effects of drug-target interactions.
What ships with it
1 file 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.
- 1mo ago First seen · 167 lines · 121 tokens per session scan A 095b82acdf58
primekg is a skill published in the GitHub repository K-Dense-AI/drug-discovery-agent-skills (48 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 1,880 once invoked, about $0.0005 per session on Opus 5.5. 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
bedpe-format-handling
Use when your ChIP-Seq input is paired-end sequencing data stored in BEDPE format (e.g., CTCFPEChIPchr2250k.bedpe.gz), and you need to estimate fragment length and call peaks while respecting the paired nature of the reads rather than treating them as independent single-end alignments.
fragment-based-count-matrix-generation
Use when you have a backed AnnData object containing processed fragment data (stored in .obsm['fragmentpaired'] or .
methylbase-object-handling
Use when after reading in per-sample methylation call files with methRead() and obtaining methylRawList objects, but before calculating differential methylation or performing annotation.
monocle3-trajectory-embedding
Use when you have an ArchR project object with dimensionality reduction results (LSI or combined dimensions from scATAC-seq ± scRNA-seq) and want to infer pseudotime trajectories and cell-state transitions.
motif-annotation-correlation-analysis
Use when you have a chromVARDeviations object with multiple annotation sets (such as JASPAR motifs and kmers) and need to determine which annotation pairs are redundant (high correlation) versus synergistic (high synergy z-scores).
motif-database-query-and-matching
Use when you have a set of differentially accessible peaks (output from differential accessibility testing, e.g., tl.