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 hannesill/m4 --skill sapsii-scoregit clone --depth 1 https://github.com/hannesill/m4Wrote 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/hannesill/m4/sapsii-score)<a href="https://agentmods.dev/skills/hannesill/m4/sapsii-score"><img src="https://agentmods.dev/badge/skills/hannesill/m4/sapsii-score/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/hannesill/m4/sapsii-score"><img src="https://agentmods.dev/badge/skills/hannesill/m4/sapsii-score.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 | $0.00035 | $0.01909 |
| Opus 5 | $0.00017 | $0.00955 |
| Sonnet 5 | $0.00007 | $0.00382 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
sapsii-score 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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAPS-II Score Calculation
The Simplified Acute Physiology Score II (SAPS-II) is a severity scoring system developed from a European/North American multicenter study. Calculated from the worst values in the first 24 hours of ICU stay.
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
- Hospital mortality prediction
- Severity stratification
- International benchmarking (widely used in European ICUs)
- Research cohort matching
- Quality improvement initiatives
Score Components (First 24 Hours)
Use the worst value in the first 24 hours of ICU admission. When both low and high extremes can score, assign the score for the qualifying extreme with the highest SAPS-II point value. Missing components are scored as 0 in M4Bench.
| Component | Value | Points |
|---|---|---|
| Age, years | < 40 | 0 |
| Age, years | 40-59 | 7 |
| Age, years | 60-69 | 12 |
| Age, years | 70-74 | 15 |
| Age, years | 75-79 | 16 |
| Age, years | >= 80 | 18 |
| Heart rate, bpm | < 40 | 11 |
| Heart rate, bpm | 40-69 | 2 |
| Heart rate, bpm | 70-119 | 0 |
| Heart rate, bpm | 120-159 | 4 |
| Heart rate, bpm | >= 160 | 7 |
| Systolic BP, mmHg | < 70 | 13 |
| Systolic BP, mmHg | 70-99 | 5 |
| Systolic BP, mmHg | 100-199 | 0 |
| Systolic BP, mmHg | >= 200 | 2 |
| Temperature, deg C | < 39.0 | 0 |
| Temperature, deg C | >= 39.0 | 3 |
| PaO2/FiO2, if ventilated or CPAP/BiPAP | < 100 | 11 |
| PaO2/FiO2, if ventilated or CPAP/BiPAP | 100-199 | 9 |
| PaO2/FiO2, if ventilated or CPAP/BiPAP | >= 200 | 6 |
| PaO2/FiO2, not ventilated/CPAP/BiPAP | Any value or missing | 0 |
| Urine output, mL/day | < 500 | 11 |
| Urine output, mL/day | 500-999 | 4 |
| Urine output, mL/day | >= 1000 | 0 |
| BUN, mg/dL | < 28 | 0 |
| BUN, mg/dL | 28-83 | 6 |
| BUN, mg/dL | >= 84 | 10 |
| WBC, x10^9/L | < 1.0 | 12 |
| WBC, x10^9/L | 1.0-19.9 | 0 |
| WBC, x10^9/L | >= 20.0 | 3 |
| Potassium, mEq/L | < 3.0 | 3 |
| Potassium, mEq/L | 3.0-4.9 | 0 |
| Potassium, mEq/L | >= 5.0 | 3 |
| Sodium, mEq/L | < 125 | 5 |
| Sodium, mEq/L | 125-144 | 0 |
| Sodium, mEq/L | >= 145 | 1 |
| Bicarbonate, mEq/L | < 15 | 6 |
| Bicarbonate, mEq/L | 15-19 | 3 |
| Bicarbonate, mEq/L | >= 20 | 0 |
| Bilirubin, mg/dL | < 4.0 | 0 |
| Bilirubin, mg/dL | 4.0-5.9 | 4 |
| Bilirubin, mg/dL | >= 6.0 | 9 |
| GCS | < 3 | Treat as missing |
| GCS | 3-5 | 26 |
| GCS | 6-8 | 13 |
| GCS | 9-10 | 7 |
| GCS | 11-13 | 5 |
| GCS | 14-15 | 0 |
| Chronic disease | AIDS | 17 |
| Chronic disease | Hematologic malignancy | 10 |
| Chronic disease | Metastatic cancer | 9 |
| Chronic disease | None of the above | 0 |
| Admission type | Scheduled surgical | 0 |
| Admission type | Medical | 6 |
| Admission type | Unscheduled surgical | 8 |
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.
- 9d ago First seen · 138 lines · 35 tokens per session scan A c3be11f6a3df
sapsii-score is a skill published in the GitHub repository hannesill/m4 (43 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,909 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.
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…
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…
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…
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…
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…
tooluniverse-cell-line-profiling
Cancer cell-line selection and profiling for experimental model choice. Cross-references DepMap, Cellosaurus, COSMIC, PharmacoDB to deliver identity verification, mutation/CNV profile, gene dependencies, drug sensitivities, and druggable targets. Use to answer 'which cell line should I use for studying gene X?' or 'is…