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 pkpd-translationgit 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/pkpd-translation)<a href="https://agentmods.dev/skills/k-dense-ai/drug-discovery-agent-skills/pkpd-translation"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/pkpd-translation/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/pkpd-translation"><img src="https://agentmods.dev/badge/skills/k-dense-ai/drug-discovery-agent-skills/pkpd-translation.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 | $0.00154 | $0.02176 |
| Opus 5 | $0.00077 | $0.01088 |
| Sonnet 5 | $0.00031 | $0.00435 |
| Haiku 4.5 | $0.00015 | $0.00218 |
Grade A, and why
pkpd-translation 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PK/PD Translation
The arithmetic between a number on a plate and a number on a label. It decides whether a compound can reach its target concentration at a dose people can tolerate — and it is where a surprising number of programmes discover, late, that it cannot.
No installation, no network, no key. Every calculation here is closed-form or a fixed-step numerical integration in the standard library. Reference: FDA, Estimating the Maximum Safe Starting Dose in Initial Clinical Trials for Therapeutics in Adult Healthy Volunteers (2005) — the Km factors are its Table 1.
Read references/nca-and-parameters.md before quoting a PK parameter, references/interspecies-scaling.md before converting a dose between species, and references/translating-potency-to-dose.md before turning an IC50 into a dose — that one is judgement, not syntax.
The four scripts
| Script | Answers |
|---|---|
nca.py |
What are this profile's clearance, volume, and half-life? |
pk_compartmental.py |
What does this regimen look like at steady state? |
allometry.py |
What is the human equivalent of this animal dose? |
exposure_margin.py |
Does the projected exposure cover the target, and is it safe? |
Free drug, or the answer is wrong by 1/fu
This is the one to get right. Only unbound drug engages the target. Comparing a total plasma concentration against a free-drug IC50 is the most common translation error, and at 99% protein binding it is a hundredfold error in the dangerous direction:
C_free = C_total x fu 1000 nM total at fu = 0.01 -> 10 nM free
Against a 100 nM IC50 that is tenfold under-coverage, not the tenfold coverage the total number
suggests. exposure_margin.py coverage takes --fu and reports both.
A related trap: 50% inhibition is rarely enough. Occupancy is C/(C+Ki), so 90% needs nine times
Ki and 95% needs nineteen. Ask what fraction the biology requires, and for how long.
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 · 161 lines · 154 tokens per session scan A 56dcdd57b3e1
pkpd-translation 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 154 tokens to every session and 2,176 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.