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 network-regulatorygit 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/network-regulatory)<a href="https://agentmods.dev/skills/inflexa-ai/inflexa/network-regulatory"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/network-regulatory/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/network-regulatory"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/network-regulatory.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 | $0.00025 | $0.01524 |
| Opus 5 | $0.00013 | $0.00762 |
| Sonnet 5 | $0.00005 | $0.00305 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
network-regulatory 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 today.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Network & Regulatory Analysis
This skill guides method selection and execution for co-expression network construction, gene regulatory network inference, protein-protein interaction analysis, and transcription factor activity scoring.
Method Selection Decision Tree
Choose the method based on your data type and analytical goal:
-
Co-expression network from bulk RNA-seq or microarray
- Use PyWGCNA for weighted correlation network construction, module detection, and hub gene identification.
- Requires variance-stabilized or log-transformed expression (NOT raw counts).
- Soft-thresholding power is chosen inside
findModules(); callWGCNA.pickSoftThreshold()directly only to inspect the fit table. The scale-free fit cut isRsquaredCut, default 0.9. - PyWGCNA is thread-parallel. Give the one process the full CPU budget of the step: raise the thread limit for that command. Do not add forked workers on top of it.
-
Co-expression from single-cell data
- Aggregate to pseudobulk first (per cluster or per sample), then apply PyWGCNA.
- Alternatively: compute correlation on top HVGs (3000-5000) from the log-normalized matrix.
- Do NOT run WGCNA directly on single-cell count matrices.
-
De novo regulon discovery is NOT available
- No tool here infers a TF-target regulon from the data alone. pySCENIC breaks against current numpy and is not installed, and it took GRNBoost2 with it.
- Say this plainly when a request asks for discovered regulons. Then offer the two routes that ARE available: scored activity from a KNOWN regulon resource (below), or co-expression modules from PyWGCNA reported AS modules.
- A co-expression module is not a regulon. It carries no motif evidence and no direction. Presenting one as a regulon is the failure this guards against.
-
TF activity scoring from a known regulon resource (single-cell and bulk)
- Use decoupler with the CollecTRI regulon resource. This is the primary regulatory route here, not a fallback.
dc.mt.ulm()ordc.mt.mlm()onadataproduces per-cell TF activity inadata.obsmunderscore_ulm/padj_ulm.- It scores the activity of regulons that CollecTRI already curates. Thus a TF absent from that resource gets no score, and the report must say which TFs the resource covered.
What ships with it
4 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.
- today First seen · 106 lines · 25 tokens per session scan A de33f11af54f
network-regulatory is a skill published in the GitHub repository inflexa-ai/inflexa (33 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 1,524 once invoked, about $0.0001 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
adverse-event-narrative
Generates CIOMS I-compliant ICSR narratives from adverse event case data for FDA and EMA regulatory submission. Includes temporal analysis, MedDRA coding, causality assessment using WHO-UMC or Naranjo criteria, and multi-format output.
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
hipaa-compliance-auditor
Clinical-grade PII/PHI detection and de-identification for healthcare text data. Scans all 18 HIPAA identifier categories with confidence scoring, generates audit logs, supports custom regex patterns, and produces de-identified output while preserving document structure.
irb-application-assistant
Assists researchers with Institutional Review Board (IRB) application tasks, including drafting informed consent documents, reviewing research protocols for compliance, generating application forms, and preparing submission checklists. Use when the user mentions IRB, Instituti...
iacuc-protocol-drafter
Draft IACUC protocol applications with focus on the 3Rs principles justification.
bulkrna-coexpression
Load when discovering gene co-expression modules and hub genes in a bulk RNA-seq cohort via WGCNA-style soft-thresholded networks. Skip when direct DE comparison (use bulkrna-de); PPI lookup of an existing gene list (use bulkrna-ppi-network); single-cell co-expression (use sc-grn).