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 agentmods add skills/hannesill/m4/ventilation-classificationnpx skills add hannesill/m4 --skill ventilation-classificationgit 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/ventilation-classification)<a href="https://agentmods.dev/skills/hannesill/m4/ventilation-classification"><img src="https://agentmods.dev/badge/skills/hannesill/m4/ventilation-classification.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.02259 |
| Opus 5 | $0.00032 | $0.01130 |
| Sonnet 5 | $0.00013 | $0.00452 |
| Haiku 4.5 | $0.00006 | $0.00226 |
Grade A, and why
ventilation-classification 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 4d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ventilation Classification
Classifies each ICU charting observation into a ventilation status category and groups consecutive observations into ventilation episodes. This concept is used directly by SOFA (respiratory component requires mechanical ventilation for scores 3-4), OASIS, and many other severity scores and research definitions.
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
- Determining ventilation type and duration for ICU stays
- SOFA respiratory scoring (requires knowing if patient is on invasive mechanical ventilation)
- Weaning studies (tracking transitions between ventilation modes)
- Respiratory support characterization in cohort studies
- Any task requiring classification of oxygen delivery or ventilator data
Ventilation Categories
| Category | Description | Examples |
|---|---|---|
| Tracheostomy | Patient has a tracheostomy tube | Tracheostomy tube, Trach mask |
| InvasiveVent | Invasive mechanical ventilation via endotracheal tube or ventilator mode | Endotracheal tube, CMV, SIMV, PRVC/AC, VOL/AC, etc. |
| NonInvasiveVent | Non-invasive positive pressure ventilation | BiPAP mask, CPAP mask, NIV modes |
| HFNC | High-flow nasal cannula | High flow nasal cannula |
| SupplementalOxygen | Low-flow or standard oxygen delivery | Nasal cannula, Non-rebreather, Face tent, Venti mask |
| None | No supplemental oxygen (room air) | None |
Classification Priority
When multiple indicators are present simultaneously, the classification follows this priority (highest first):
- Tracheostomy —
o2_delivery_device_1is 'Tracheostomy tube' or 'Trach mask ' - InvasiveVent —
o2_delivery_device_1is 'Endotracheal tube' OR any invasive ventilator mode present - NonInvasiveVent —
o2_delivery_device_1is 'Bipap mask ' or 'CPAP mask ' OR Hamilton NIV modes - HFNC —
o2_delivery_device_1is 'High flow nasal cannula' - SupplementalOxygen — Other oxygen delivery devices
- None —
o2_delivery_device_1is 'None'
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.
- 4d ago First seen · 150 lines · 64 tokens per session scan A 0d7df5123964
ventilation-classification is a skill published in the GitHub repository hannesill/m4 (43 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 2,259 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 2026-08-30.
Other skills, from other repositories
experiment_management
Set up and manage the experiment folder structure. This is Phase 0 — it runs before any analysis begins. All bookkeeping files are JSON (never markdown).
evaluate
Compare baseline and new implementation results. Produce the machine-readable final report result.json, update experiments.json, and append a row to comparison.json.
implement
Create a new Jupyter notebook implementing the method from the research paper, using the same data as the baseline. Record implementation details and measured metrics as a structured JSON entry.
progress
Maintain a machine-readable progress file so dashboards, CLIs, and notebooks can poll the experiment's state at any time. The file is a JSON document — never markdown, never human-prose-first.
optimize
Drive structured autoresearch iteration after evo:discover and the baseline commit. Use when the user invokes /evo:optimize or asks to try ideas, try variants, run experiments, use available GPUs, improve the current best/frontier, continue an evo search, or compare candidate changes in an evo workspace. The…
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…