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 first-icu-staygit 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/first-icu-stay)<a href="https://agentmods.dev/skills/hannesill/m4/first-icu-stay"><img src="https://agentmods.dev/badge/skills/hannesill/m4/first-icu-stay/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/first-icu-stay"><img src="https://agentmods.dev/badge/skills/hannesill/m4/first-icu-stay.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00034 | $0.01308 |
| Opus 5 | $0.00017 | $0.00654 |
| Sonnet 5 | $0.00007 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
first-icu-stay 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.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First ICU Stay Selection
Identifies first ICU stays and hospital admissions for cohort construction. Critical for avoiding correlated observations and inflated sample sizes from readmissions.
When to Use This Skill
- Creating research cohorts with independent observations
- Excluding readmissions that may have different characteristics
- Selecting incident (first-time) ICU patients
- Matching cohorts by admission characteristics
Pre-computed Table
SELECT
subject_id,
hadm_id,
stay_id,
-- Demographics
gender,
dod, -- Date of death (if applicable)
-- Hospital admission
admittime,
dischtime,
los_hospital, -- Hospital length of stay (days)
admission_age,
race,
hospital_expire_flag,
hospstay_seq, -- Hospital admission sequence number
first_hosp_stay, -- TRUE if first hospitalization
-- ICU stay
icu_intime,
icu_outtime,
los_icu, -- ICU length of stay (days)
icustay_seq, -- ICU stay sequence within hospitalization
first_icu_stay -- TRUE if first ICU stay of this hospitalization
FROM mimiciv_derived.icustay_detail;
Key Columns Explained
Hospital-Level
hospstay_seq: Order of hospital admission for this patient (1 = first ever)first_hosp_stay: TRUE if this is the patient's first hospital admission
ICU-Level (Within Hospitalization)
icustay_seq: Order of ICU stays within this hospitalization (1 = first ICU stay)first_icu_stay: TRUE if this is the first ICU stay of the current hospitalization
Age Calculation
Age is calculated as:
anchor_age + (YEAR(admittime) - anchor_year)
Important: MIMIC-IV shifts ages for patients > 89 years old at any admission. These patients have anchor_age = 91 and ages are not exact.
Common Cohort Selection Patterns
First ICU Stay Only (Most Common)
SELECT *
FROM mimiciv_derived.icustay_detail
WHERE first_icu_stay = TRUE;
First-Ever ICU Stay (Strictest)
SELECT *
FROM mimiciv_derived.icustay_detail
WHERE first_hosp_stay = TRUE
AND first_icu_stay = TRUE;
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 188 lines · 34 tokens per session scan A 315ed224c1d1
first-icu-stay is a skill published in the GitHub repository hannesill/m4 (43 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,308 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
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
arbor-research-agent
Public entrypoint for the Arbor skill suite. Use when a user wants to run an Arbor-style autonomous research or optimization workflow from a natural-language goal, including initial clarification of objective, target project, data, metric, evaluation, permissions, budget, run mode, and then automatic bootstrapping…
arbor-agent-executor
Executor-dispatch phase for Arbor. Use when implementing an Idea Tree node through RunExecutor or RunExecutorParallel semantics: isolated git worktree, executor prompt construction, eval metadata injection, RunTraining policy, smoke/full evaluation, report parsing, artifact persistence, tree update, and insight…
arbor-agent-setup-intake
Setup, intake, preflight, and launch-contract phase for open-source Arbor runs. Use when confirming a target project, metric, baseline, dev/test split, config/plugin settings, branch guard, session directory, or when translating a user goal into the precise contract consumed by the coordinator.
arbor-agent-ideate
Strict IDEATE-stage skill for Arbor. Use immediately after TreeView(format="constraints") when drafting Idea Tree nodes, enforcing the ideadrafting and firstprinciplesprobe behavior, depth-aware idea levels, four-line TreeAddNode hypotheses, conflict checks, and self-filtering against shallow tweaks.
arbor-agent-merge-eval
Merge and evaluation discipline for Arbor. Use for TreeSetMeta metadata, Bdev/Btest separation, eval command templates, score parsing, GitMergeBranch behavior, protected paths, required outputs, metricdirection, trunk/test score updates, medal detection, and final evaluation before stopping.