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 inflexa-ai/inflexa --skill pkpd-clinical-responsegit clone --depth 1 https://github.com/inflexa-ai/inflexaWrote 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/inflexa-ai/inflexa/pkpd-clinical-response)<a href="https://agentmods.dev/skills/inflexa-ai/inflexa/pkpd-clinical-response"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/pkpd-clinical-response/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/inflexa-ai/inflexa/pkpd-clinical-response"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/pkpd-clinical-response.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00057 | $0.02766 |
| Opus 5 | $0.00028 | $0.01383 |
| Sonnet 5 | $0.00011 | $0.00553 |
| Haiku 4.5 | $0.00006 | $0.00277 |
Grade A, and why
pkpd-clinical-response 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 2d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PK/PD & Clinical Response
This skill guides pharmacokinetic/pharmacodynamic data analysis and clinical response evaluation in Phase 1/2 trial-adjacent contexts.
Clinical Response Classification
RECIST 1.1 (Response Evaluation Criteria in Solid Tumors)
Reference: references/clinical-response-criteria.md — read it for full RECIST 1.1 tables, overall response derivation matrix, recist_classify_target(), best_overall_response(), and iRECIST pseudoprogression rules.
| Category | Abbreviation | Definition |
|---|---|---|
| Complete Response | CR | Disappearance of all target lesions |
| Partial Response | PR | >=30% decrease in sum of diameters |
| Stable Disease | SD | Neither PR nor PD criteria met |
| Progressive Disease | PD | >=20% increase in sum + absolute increase >=5mm, or new lesion |
When response data is present:
- Binary: responder (CR+PR) vs non-responder (SD+PD)
- Ordinal: CR > PR > SD > PD (use ordinal logistic regression)
- Duration: time to best response, duration of response
iRECIST (for immunotherapy)
Adds "unconfirmed" states (iUPD → must confirm with iCPD at next assessment). For IO trials, always check if iRECIST was used.
Pharmacokinetic Analysis
Non-Compartmental Analysis (NCA)
Reference: references/nca-analysis.md — read it for complete NCA functions (auc_linear_trapezoidal, auc_log_linear_trapezoidal, auc_extrapolated, terminal_half_life, derive_pk_params), concentration-time plots, and quality checks.
Always report: Cmax, Tmax, AUC(0-last), AUC(0-inf), t1/2, CL/F, Vd/F. Plot: concentration-time profile (linear and semi-log scale).
Population PK and Covariates
Two different methods share this name. Pick on the sampling design, then read the matching reference:
Concentration-time data + patient covariates
├── Rich sampling (each subject's own PK parameters are well estimated)
│ ├── Question is "which covariates explain the spread in CL/Vd?"
│ │ └── Two-stage: derive per-subject parameters by NCA, then regress
│ │ them on covariates → references/population-pk.md
│ └── Question is about the PK model itself — structure, IIV, or what a
│ different regimen would give
│ └── NLME with nlmixr2 → references/population-pk-nlme.md
└── Sparse sampling (few points per subject)
└── NLME only. Two-stage cannot estimate per-subject parameters to
regress, and treating imprecise ones as observed biases covariate
effects toward the null → references/population-pk-nlme.md
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.
- 2d ago First seen · 215 lines · 57 tokens per session scan A 3d3671752133
pkpd-clinical-response is a skill published in the GitHub repository inflexa-ai/inflexa (33 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 2,766 once invoked, about $0.0003 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 2026-09-09.
Other skills, from other repositories
admet-prediction
Predict comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties for drug candidate molecules using GraphMVP ensemble models. Use this skill when: (1) Predicting blood-brain barrier penetration, (2) Assessing side effect profiles, (3) Estimating Caco-2 permeability, half-life, or LD50…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.