mimic-ventilation

mimic-ventilation is a skill for Claude Code, Codex from hannesill/m4. It costs 0 tokens per session (1,377 once invoked), scanned A, a copy of mimic-apsiii-24h-raw, MIT.

A SQL query for the MIMIC-IV clinical database that classifies patients' ventilation and groups consecutive observations into episodes. MIMIC-IV is a database of de-identified hospital intensive-care records.

In plain words
What is it for?
It helps classify invasive and non-invasive ventilation, high-flow nasal cannula, supplemental oxygen, tracheostomy, and no ventilation.
Why use it?
It provides a consistent way to identify different forms of breathing support from charted clinical data.

Skill for Claude CodeCodex

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

Good fit It helps classify invasive and non-invasive ventilation, high-flow nasal cannula, supplemental oxygen, tracheostomy, and no ventilation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hannesill/m4/mimic-ventilation
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 mimic-ventilation
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 mimic-ventilation

README.md
[![agentmods](https://agentmods.dev/badge/skills/hannesill/m4/mimic-ventilation.svg)](https://agentmods.dev/skills/hannesill/m4/mimic-ventilation)
Your own site
<a href="https://agentmods.dev/skills/hannesill/m4/mimic-ventilation"><img src="https://agentmods.dev/badge/skills/hannesill/m4/mimic-ventilation.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,377 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 100% copy Near-identical to another mod 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 $0.00000 $0.01377
Opus 5 $0.00000 $0.00688
Sonnet 5 $0.00000 $0.00275
Haiku 4.5 $0.00000 $0.00138

Measured 8d ago against content hash 853c4709e0ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mimic-ventilation 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.

Origin

This is a copy

100% identical to mimic-apsiii-24h-raw — 976 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

benchmark/tasks/ventilation/mimic-ventilation/skills-rawsql/mimic-ventilation/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reference SQL (matched-content control)

The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.

-- ------------------------------------------------------------------
-- Title: Ventilation Classification
-- Classifies ventilation status from charting data and groups
-- consecutive observations into episodes. Categories: InvasiveVent,
-- NonInvasiveVent, HFNC, SupplementalOxygen, Tracheostomy, None.
-- ------------------------------------------------------------------

-- Reference:
--    MIT-LCP mimic-code ventilation concept definition.

-- Adapted from mimic-code ventilation.sql
-- Adds ventilation_seq column for deterministic row matching.

WITH tm AS (
  SELECT
    stay_id,
    charttime
  FROM mimiciv_derived.ventilator_setting
  UNION
  SELECT
    stay_id,
    charttime
  FROM mimiciv_derived.oxygen_delivery
), vs AS (
  SELECT
    tm.stay_id,
    tm.charttime,
    o2_delivery_device_1,
    COALESCE(ventilator_mode, ventilator_mode_hamilton) AS vent_mode,
    CASE
      WHEN o2_delivery_device_1 IN ('Tracheostomy tube', 'Trach mask ')
      THEN 'Tracheostomy'
      WHEN o2_delivery_device_1 IN ('Endotracheal tube')
      OR ventilator_mode IN ('(S) CMV', 'APRV', 'APRV/Biphasic+ApnPress', 'APRV/Biphasic+ApnVol', 'APV (cmv)', 'Ambient', 'Apnea Ventilation', 'CMV', 'CMV/ASSIST', 'CMV/ASSIST/AutoFlow', 'CMV/AutoFlow', 'CPAP/PPS', 'CPAP/PSV', 'CPAP/PSV+Apn TCPL', 'CPAP/PSV+ApnPres', 'CPAP/PSV+ApnVol', 'MMV', 'MMV/AutoFlow', 'MMV/PSV', 'MMV/PSV/AutoFlow', 'P-CMV', 'PCV+', 'PCV+/PSV', 'PCV+Assist', 'PRES/AC', 'PRVC/AC', 'PRVC/SIMV', 'PSV/SBT', 'SIMV', 'SIMV/AutoFlow', 'SIMV/PRES', 'SIMV/PSV', 'SIMV/PSV/AutoFlow', 'SIMV/VOL', 'SYNCHRON MASTER', 'SYNCHRON SLAVE', 'VOL/AC')
      OR ventilator_mode_hamilton IN ('APRV', 'APV (cmv)', 'Ambient', '(S) CMV', 'P-CMV', 'SIMV', 'APV (simv)', 'P-SIMV', 'VS', 'ASV')
      THEN 'InvasiveVent'
      WHEN o2_delivery_device_1 IN ('Bipap mask ', 'CPAP mask ')
      OR ventilator_mode_hamilton IN ('DuoPaP', 'NIV', 'NIV-ST')
      THEN 'NonInvasiveVent'
      WHEN o2_delivery_device_1 IN ('High flow nasal cannula')
      THEN 'HFNC'
      WHEN o2_delivery_device_1 IN ('Non-rebreather', 'Face tent', 'Aerosol-cool', 'Venti mask ', 'Medium conc mask ', 'Ultrasonic neb', 'Vapomist', 'Oxymizer', 'High flow neb', 'Nasal cannula')
      THEN 'SupplementalOxygen'
      WHEN o2_delivery_device_1 IN ('None')
      THEN 'None'
      ELSE NULL
    END AS ventilation_status
  FROM tm
  LEFT JOIN mimiciv_derived.ventilator_setting AS vs
    ON tm.stay_id = vs.stay_id AND tm.charttime = vs.charttime
  LEFT JOIN mimiciv_derived.oxygen_delivery AS od
    ON tm.stay_id = od.stay_id AND tm.charttime = od.charttime
), vd0 AS (
  SELECT
    stay_id,
    charttime,
    LAG(charttime, 1) OVER (PARTITION BY stay_id, ventilation_status ORDER BY charttime NULLS FIRST) AS charttime_lag,
    LEAD(charttime, 1) OVER w AS charttime_lead,
    ventilation_status,
    LAG(ventilation_status, 1) OVER w AS ventilation_status_lag
  FROM vs
  WHERE
    NOT ventilation_status IS NULL
  WINDOW w AS (PARTITION BY stay_id ORDER BY charttime NULLS FIRST)
), vd1 AS (
  SELECT
    stay_id,
    charttime,
    charttime_lag,
    charttime_lead,
    ventilation_status,
    DATE_DIFF('microseconds', charttime_lag, charttime)/60000000.0 / 60 AS ventduration,
    CASE
      WHEN ventilation_status_lag IS NULL
      THEN 1
      WHEN DATE_DIFF('microseconds', charttime_lag, charttime)/3600000000.0 >= 14
      THEN 1
      WHEN ventilation_status_lag <> ventilation_status
      THEN 1
      ELSE 0
    END AS new_ventilation_event
  FROM vd0
), vd2 AS (
  SELECT
    vd1.stay_id,
    vd1.charttime,
    vd1.charttime_lead,
    vd1.ventilation_status,
    ventduration,
    new_ventilation_event,
    SUM(new_ventilation_event) OVER (PARTITION BY stay_id ORDER BY charttime NULLS FIRST) AS vent_seq
  FROM vd1
), episodes AS (
  SELECT
    stay_id,
    MIN(charttime) AS starttime,
    MAX(
      CASE
        WHEN charttime_lead IS NULL
        OR DATE_DIFF('microseconds', charttime, charttime_lead)/3600000000.0 >= 14
        THEN charttime
        ELSE charttime_lead
      END
    ) AS endtime,
    MAX(ventilation_status) AS ventilation_status
  FROM vd2
  GROUP BY
    stay_id,
    vent_seq
  HAVING
    MIN(charttime) <> MAX(charttime)
)
SELECT
  stay_id,
  ROW_NUMBER() OVER (PARTITION BY stay_id ORDER BY starttime) AS ventilation_seq,
  starttime,
  endtime,
  ventilation_status
FROM episodes

Read the full file on GitHub · 129 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. 8d ago First seen · 129 lines · 0 tokens per session scan A 853c4709e0ab

Subscribe to this mod's changes

mimic-ventilation is a skill published in the GitHub repository hannesill/m4 (43 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,377 tokens. A static security scan graded it A with 0 findings. It is 100% identical to mimic-apsiii-24h-raw, differing in 976 lines, and is treated as a copy.

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

embeddings

Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.

ruvnet/ruflo · 62 tokens

cqrs-implementation

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

wshobson/agents · 35 tokens

projection-patterns

Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.

wshobson/agents · 36 tokens

migration-review

Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.

rohitg00/ai-engineering-from-scratch · 35 tokens

azure-resource-manager-postgresql-dotnet

Azure PostgreSQL Flexible Server SDK for .NET. Database management for PostgreSQL Flexible Server deployments. Use for creating servers, databases, firewall rules, configurations, backups, and high availability. Triggers: "PostgreSQL", "PostgreSqlFlexibleServer", "PostgreSQL Flexible Server", "Azure Database for…

microsoft/skills · 97 tokens