sepsis-3-cohort

sepsis-3-cohort is a skill for Claude Code, Codex from hannesill/m4. It costs 41 tokens per session (2,021 once invoked), scanned A, original, MIT.

A clinical cohort definition for finding patients who meet the Sepsis-3 research criteria. Sepsis-3 describes sepsis as organ dysfunction caused by an abnormal response to infection, using suspected infection plus a SOFA score of at least 2.

In plain words
What is it for?
Use it to identify sepsis cohorts, support outcome research, and calculate quality metrics from available clinical tables and source data.
Why use it?
It turns a medical definition into a reproducible data-selection rule for studies and quality measurement. It also distinguishes related concepts such as qSOFA and septic shock.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to identify sepsis cohorts, support outcome research, and calculate quality metrics from available clinical tables and source data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hannesill/m4/sepsis-3-cohort
View source ↗ hannesill/m4
Install

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.

Any agent
npx skills add hannesill/m4 --skill sepsis-3-cohort
Clone the repo
git clone --depth 1 https://github.com/hannesill/m4

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sepsis-3-cohort

README.md
[![agentmods](https://agentmods.dev/badge/skills/hannesill/m4/sepsis-3-cohort/github.svg)](https://agentmods.dev/skills/hannesill/m4/sepsis-3-cohort)
Your own site
<a href="https://agentmods.dev/skills/hannesill/m4/sepsis-3-cohort"><img src="https://agentmods.dev/badge/skills/hannesill/m4/sepsis-3-cohort/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.

agentmods 80×15 button for sepsis-3-cohort

Your own site · 80×15
<a href="https://agentmods.dev/skills/hannesill/m4/sepsis-3-cohort"><img src="https://agentmods.dev/badge/skills/hannesill/m4/sepsis-3-cohort.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,021 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.02021
Opus 5 $0.00020 $0.01010
Sonnet 5 $0.00008 $0.00404
Haiku 4.5 $0.00004 $0.00202

Measured 11d ago against content hash cd006c6b656a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sepsis-3-cohort 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 11d 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.

benchmark/tasks/sepsis3/mimic-sepsis3-raw/skills/sepsis-3-cohort/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sepsis-3 Cohort Identification

The Sepsis-3 definition (Singer et al. 2016) identifies sepsis as life-threatening organ dysfunction caused by a dysregulated host response to infection. This is a conceptual definition; the operationalization is a proxy:

  • Suspected infection (antibiotics + culture within time window) AND
  • SOFA score >= 2 (within 48h before to 24h after suspected infection)

Related Sepsis-3 Constructs

  • qSOFA (quick SOFA): Bedside screening tool for patients outside the ICU (RR >= 22, altered mentation, SBP <= 100). Not a diagnostic criterion — meant to prompt further assessment. Sensitivity is limited; a negative qSOFA does not rule out sepsis.
  • Septic Shock: Sepsis with vasopressor requirement to maintain MAP >= 65 mmHg AND lactate > 2 mmol/L despite adequate fluid resuscitation. Carries substantially higher mortality than sepsis alone.

M4Bench Use

In M4Bench, target concept tables listed in the task configuration are removed or unavailable in the agent database. Use this skill as procedural guidance and derive the requested output from available source or intermediate tables; do not rely on a precomputed target table or bundled SQL script.

When to Use This Skill

  • Creating sepsis patient cohorts for research
  • Sepsis outcome studies
  • Quality improvement and benchmarking
  • Comparing sepsis populations across studies
  • Validating machine learning models on sepsis data

Sepsis-3 Definition Details

Suspected Infection Criteria

A patient has suspected infection when:

  1. Antibiotics are administered (systemic, excluding topical) AND
  2. Cultures are obtained within a time window:
    • Culture within 72h BEFORE antibiotic, OR
    • Culture within 24h AFTER antibiotic

See suspicion-of-infection for detailed matching logic.

SOFA Criteria

SOFA >= 2 points, where SOFA is calculated using 24-hour worst values:

  • Must occur within 48h before to 24h after suspected infection time

Read the full file on GitHub · 132 lines

Changes

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.

  1. 11d ago First seen · 132 lines · 41 tokens per session scan A cd006c6b656a

Subscribe to this mod's changes

sepsis-3-cohort is a skill published in the GitHub repository hannesill/m4 (43 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 2,021 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

arbor-agent-orchestrator

Top-level controller for recreating the open-source AutoResearch workflow as a suite of skills. Use when the user asks to run, emulate, extract, validate, or refine Arbor/AutoResearch behavior, especially when a coordinator must load phase skills for setup, ideation, executors, merge evaluation, novelty search…

RUC-NLPIR/Arbor · 77 tokens

dfam-check

Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an .stl, .obj, .ply, or .3mf mesh, wants a build-orientation…

earthtojake/text-to-cad · 111 tokens

tooluniverse-phylogenetics

Phylogenetic analysis — de novo multiple sequence alignment (Clustal Omega/MUSCLE/MAFFT via EBImsaalign) and neighbour-joining/UPGMA tree building (EBIbuildphylogenetictree) from your own sequences, plus tree analysis, treeness, saturation (PhyKIT), parsimony-informative sites, alignment gap analysis, DVMC…

mims-harvard/ToolUniverse · 155 tokens

tooluniverse-gene-enrichment

Gene-set enrichment analysis — GO (Biological Process, Molecular Function, Cellular Component), KEGG, Reactome pathway enrichment via clusterProfiler, gseapy, ORA, GSEA. Use for interpreting DEG lists, screen hit lists, or any gene-list-to-pathways query. Includes simplify-cutoff handling and union-vs-total…

mims-harvard/ToolUniverse · 82 tokens

tooluniverse-population-genetics

Population genetics analysis — allele frequencies (gnomAD, 1000 Genomes), Hardy-Weinberg equilibrium testing, Fst between populations, GWAS associations, evolutionary constraint scores. Use for cross-population variant comparison, ancestry-aware allele frequency lookups, and population-level evolutionary analysis.

mims-harvard/ToolUniverse · 66 tokens

tooluniverse-variant-analysis

VCF and variant analysis — parsing, annotation, classification (synonymous, missense, frameshift, stopgained), VAF filtering, coding vs non-coding categorization, multi-condition variant comparison. Use for VCF parsing, variant fraction calculations (denominator = coding subset only, NOT all variants), and per-sample…

mims-harvard/ToolUniverse · 77 tokens