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 apsiii-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/apsiii-score)<a href="https://agentmods.dev/skills/hannesill/m4/apsiii-score"><img src="https://agentmods.dev/badge/skills/hannesill/m4/apsiii-score.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00895 |
| Opus 5 | $0.00020 | $0.00447 |
| Sonnet 5 | $0.00008 | $0.00179 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
apsiii-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 8d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APACHE III (APS III) Score Calculation
The Acute Physiology Score III (APS III) is the physiological component of APACHE III. It measures patient severity of illness on the first day of ICU stay and provides hospital mortality probability estimates.
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 and risk adjustment
- Case-mix adjustment for benchmarking
- Comparing outcomes across ICUs or time periods
- Research cohort severity matching
Score Components
The APS III uses the worst values from the first 24 hours of ICU stay:
Vital Signs
- Heart rate (normal reference: 75 bpm)
- Mean blood pressure (normal reference: 90 mmHg)
- Temperature (normal reference: 38C)
- Respiratory rate (normal reference: 19 breaths/min)
Laboratory Values
- Hematocrit (normal reference: 45.5%)
- WBC (normal reference: 11.5 x10^9/L)
- Creatinine (normal reference: 1.0 mg/dL)
- BUN (scored from 0, higher is worse)
- Sodium (normal reference: 145.5 mEq/L)
- Albumin (normal reference: 3.5 g/dL)
- Bilirubin (scored from 0, higher is worse)
- Glucose (normal reference: 130 mg/dL)
Blood Gas
- PaO2 (for non-ventilated patients with FiO2 < 50%)
- A-aDO2 (for ventilated patients with FiO2 >= 50%)
- pH and PaCO2 interaction scoring
Other
- GCS (complex interaction between eye, verbal, motor components)
- Urine output (24-hour total)
- Mechanical ventilation status
- Acute renal failure flag
Critical Implementation Notes
- Worst Value Definition: "Worst" means furthest from a predefined normal reference value, not simply min or max. For example:
- Heart rate worst = MAX(|HR - 75|)
- If equally distant from normal, use the higher score
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.
- 8d ago First seen · 86 lines · 41 tokens per session scan A 8ecc5163915f
apsiii-score 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 895 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…