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 mimic-ventilationgit 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/mimic-ventilation)<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>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 | $0.00000 | $0.01377 |
| Opus 5 | $0.00000 | $0.00688 |
| Sonnet 5 | $0.00000 | $0.00275 |
| Haiku 4.5 | $0.00000 | $0.00138 |
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.
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.
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
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 · 129 lines · 0 tokens per session scan A 853c4709e0ab
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.
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…
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.
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.
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.
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.
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…