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-suspicion-infection-rawgit 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-suspicion-infection-raw)<a href="https://agentmods.dev/skills/hannesill/m4/mimic-suspicion-infection-raw"><img src="https://agentmods.dev/badge/skills/hannesill/m4/mimic-suspicion-infection-raw/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/mimic-suspicion-infection-raw"><img src="https://agentmods.dev/badge/skills/hannesill/m4/mimic-suspicion-infection-raw.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01664 |
| Opus 5 | $0.00000 | $0.00832 |
| Sonnet 5 | $0.00000 | $0.00333 |
| Haiku 4.5 | $0.00000 | $0.00166 |
Grade A, and why
mimic-suspicion-infection-raw 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 12d 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 — 1,042 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 — 177 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: Suspicion of Infection
-- Identifies suspected infection events by pairing systemic antibiotic
-- administration with culture collection within asymmetric time windows:
-- culture within 72h before OR 24h after antibiotic start.
-- ------------------------------------------------------------------
-- Reference:
-- Seymour CW et al. "Assessment of Clinical Criteria for Sepsis."
-- JAMA. 2016;315(8):762-774.
-- Adapted from mimic-code suspicion_of_infection.sql
-- Optimized for DuckDB: split OR joins into UNION ALL for IEJoin.
-- DEVIATION from mimic-code: ROW_NUMBER() orderings include stable tie-breakers
-- so exact timestamp/name ties select deterministically across execution plans.
WITH ab_tbl AS (
SELECT
abx.subject_id,
abx.hadm_id,
abx.stay_id,
abx.antibiotic,
abx.starttime AS antibiotic_time,
DATE_TRUNC('DAY', abx.starttime) AS antibiotic_date,
abx.stoptime AS antibiotic_stoptime,
ROW_NUMBER() OVER (
PARTITION BY subject_id
ORDER BY
starttime NULLS FIRST,
stoptime NULLS FIRST,
antibiotic NULLS FIRST,
hadm_id NULLS FIRST,
stay_id NULLS FIRST
) AS ab_id
FROM mimiciv_derived.antibiotic AS abx
), me AS (
SELECT
micro_specimen_id,
MAX(subject_id) AS subject_id,
MAX(hadm_id) AS hadm_id,
TRY_CAST(MAX(chartdate) AS DATE) AS chartdate,
MAX(charttime) AS charttime,
MAX(spec_type_desc) AS spec_type_desc,
MAX(
CASE
WHEN NOT org_name IS NULL AND org_itemid <> 90856 AND org_name <> ''
THEN 1
ELSE 0
END
) AS positiveculture
FROM mimiciv_hosp.microbiologyevents
GROUP BY
micro_specimen_id
),
-- Split me into two subsets so each join path uses only simple inequalities
-- (no OR), enabling DuckDB's IEJoin range-join optimization.
me_with_time AS (
SELECT * FROM me WHERE charttime IS NOT NULL
),
me_date_only AS (
SELECT * FROM me WHERE charttime IS NULL
),
me_then_ab AS (
SELECT
subject_id, hadm_id, stay_id, ab_id, micro_specimen_id,
last72_charttime, last72_positiveculture, last72_specimen,
ROW_NUMBER() OVER (
PARTITION BY subject_id, ab_id
ORDER BY chartdate NULLS FIRST, charttime NULLS FIRST, micro_specimen_id NULLS FIRST
) AS micro_seq
FROM (
-- Cultures with charttime: antibiotic within 72h after culture
SELECT
ab_tbl.subject_id, ab_tbl.hadm_id, ab_tbl.stay_id, ab_tbl.ab_id,
me72.micro_specimen_id,
me72.charttime AS last72_charttime,
me72.positiveculture AS last72_positiveculture,
me72.spec_type_desc AS last72_specimen,
me72.chartdate,
me72.charttime
FROM ab_tbl
INNER JOIN me_with_time AS me72
ON ab_tbl.subject_id = me72.subject_id
AND ab_tbl.antibiotic_time > me72.charttime
AND ab_tbl.antibiotic_time <= me72.charttime + INTERVAL '72' HOUR
UNION ALL
-- Cultures with only chartdate: antibiotic within 3 days after culture
SELECT
ab_tbl.subject_id, ab_tbl.hadm_id, ab_tbl.stay_id, ab_tbl.ab_id,
me72.micro_specimen_id,
CAST(me72.chartdate AS TIMESTAMP) AS last72_charttime,
me72.positiveculture AS last72_positiveculture,
me72.spec_type_desc AS last72_specimen,
me72.chartdate,
me72.charttime
FROM ab_tbl
INNER JOIN me_date_only AS me72
ON ab_tbl.subject_id = me72.subject_id
AND ab_tbl.antibiotic_date >= me72.chartdate
AND ab_tbl.antibiotic_date <= me72.chartdate + INTERVAL 3 DAY
)
),
ab_then_me AS (
SELECT
subject_id, hadm_id, stay_id, ab_id, micro_specimen_id,
next24_charttime, next24_positiveculture, next24_specimen,
ROW_NUMBER() OVER (
PARTITION BY subject_id, ab_id
ORDER BY chartdate NULLS FIRST, charttime NULLS FIRST, micro_specimen_id NULLS FIRST
) AS micro_seq
FROM (
-- Cultures with charttime: antibiotic within 24h before culture
SELECT
ab_tbl.subject_id, ab_tbl.hadm_id, ab_tbl.stay_id, ab_tbl.ab_id,
me24.micro_specimen_id,
me24.charttime AS next24_charttime,
me24.positiveculture AS next24_positiveculture,
me24.spec_type_desc AS next24_specimen,
me24.chartdate,
me24.charttime
FROM ab_tbl
INNER JOIN me_with_time AS me24
ON ab_tbl.subject_id = me24.subject_id
AND ab_tbl.antibiotic_time >= me24.charttime - INTERVAL '24' HOUR
AND ab_tbl.antibiotic_time < me24.charttime
UNION ALL
-- Cultures with only chartdate: antibiotic within 1 day before culture
SELECT
ab_tbl.subject_id, ab_tbl.hadm_id, ab_tbl.stay_id, ab_tbl.ab_id,
me24.micro_specimen_id,
CAST(me24.chartdate AS TIMESTAMP) AS next24_charttime,
me24.positiveculture AS next24_positiveculture,
me24.spec_type_desc AS next24_specimen,
me24.chartdate,
me24.charttime
FROM ab_tbl
INNER JOIN me_date_only AS me24
ON ab_tbl.subject_id = me24.subject_id
AND ab_tbl.antibiotic_date >= me24.chartdate - INTERVAL 1 DAY
AND ab_tbl.antibiotic_date <= me24.chartdate
)
)
SELECT
ab_tbl.subject_id,
ab_tbl.stay_id,
ab_tbl.hadm_id,
ab_tbl.ab_id,
ab_tbl.antibiotic,
ab_tbl.antibiotic_time,
CASE WHEN last72_specimen IS NULL AND next24_specimen IS NULL THEN 0 ELSE 1 END AS suspected_infection,
CASE
WHEN last72_specimen IS NULL AND next24_specimen IS NULL
THEN NULL
ELSE COALESCE(last72_charttime, antibiotic_time)
END AS suspected_infection_time,
COALESCE(last72_charttime, next24_charttime) AS culture_time,
COALESCE(last72_specimen, next24_specimen) AS specimen,
COALESCE(last72_positiveculture, next24_positiveculture) AS positive_culture
FROM ab_tbl
LEFT JOIN ab_then_me AS ab2me
ON ab_tbl.subject_id = ab2me.subject_id
AND ab_tbl.ab_id = ab2me.ab_id
AND ab2me.micro_seq = 1
LEFT JOIN me_then_ab AS me2ab
ON ab_tbl.subject_id = me2ab.subject_id
AND ab_tbl.ab_id = me2ab.ab_id
AND me2ab.micro_seq = 1
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.
- 12d ago First seen · 177 lines · 0 tokens per session scan A 025c4c9b48fa
mimic-suspicion-infection-raw 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 1,664 tokens. A static security scan graded it A with 0 findings. It is 100% identical to mimic-apsiii-24h-raw, differing in 1,042 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…
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-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-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-population-genetics
Population genetics analysis — allele frequencies (gnomAD, 1000 Genomes), Hardy-Weinberg equilibrium testing, Fst between populations, GWAS associations, evolutionary constraint scores. Use for cross-population variant comparison, ancestry-aware allele frequency lookups, and population-level evolutionary analysis.
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…