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-meld-24h-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-meld-24h-raw)<a href="https://agentmods.dev/skills/hannesill/m4/mimic-meld-24h-raw"><img src="https://agentmods.dev/badge/skills/hannesill/m4/mimic-meld-24h-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-meld-24h-raw"><img src="https://agentmods.dev/badge/skills/hannesill/m4/mimic-meld-24h-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 | $0.00839 |
| Opus 5 | $0.00000 | $0.00419 |
| Sonnet 5 | $0.00000 | $0.00168 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
mimic-meld-24h-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 11d 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 — 963 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.
What it actually says
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: Model for End-Stage Liver Disease (MELD) score
-- This query extracts the MELD-Na score for the first 24 hours of
-- each ICU stay. MELD uses logarithmic transformations of creatinine,
-- bilirubin, and INR with a conditional sodium adjustment.
-- ------------------------------------------------------------------
-- Reference for MELD:
-- Kamath PS et al. "A model to predict survival in patients with
-- end-stage liver disease." Hepatology. 2001;33(2):464-470.
-- Kim WR et al. "Hyponatremia and mortality among patients on the
-- liver-transplant waiting list." NEJM. 2008;359(10):1018-1026.
-- Adapted from mimic-code meld.sql
WITH cohort AS (
SELECT
ie.subject_id,
ie.hadm_id,
ie.stay_id,
labs.creatinine_max,
labs.bilirubin_total_max,
labs.inr_max,
labs.sodium_min,
r.dialysis_present AS rrt
FROM mimiciv_icu.icustays AS ie
LEFT JOIN mimiciv_derived.first_day_lab AS labs
ON ie.stay_id = labs.stay_id
LEFT JOIN mimiciv_derived.first_day_rrt AS r
ON ie.stay_id = r.stay_id
)
, score AS (
SELECT
subject_id, hadm_id, stay_id,
rrt, creatinine_max, bilirubin_total_max, inr_max, sodium_min,
CASE
WHEN sodium_min IS NULL THEN 0.0
WHEN sodium_min > 137 THEN 0.0
WHEN sodium_min < 125 THEN 12.0
ELSE 137.0 - sodium_min
END AS sodium_score,
CASE
WHEN rrt = 1 OR creatinine_max > 4.0
THEN (0.957 * LN(4))
WHEN creatinine_max < 1
THEN (0.957 * LN(1))
ELSE 0.957 * COALESCE(LN(creatinine_max), LN(1))
END AS creatinine_score,
CASE
WHEN bilirubin_total_max < 1
THEN 0.378 * LN(1)
ELSE 0.378 * COALESCE(LN(bilirubin_total_max), LN(1))
END AS bilirubin_score,
CASE
WHEN inr_max < 1
THEN (1.120 * LN(1) + 0.643)
ELSE (1.120 * COALESCE(LN(inr_max), LN(1)) + 0.643)
END AS inr_score
FROM cohort
)
, score2 AS (
SELECT
subject_id, hadm_id, stay_id,
rrt, creatinine_max, bilirubin_total_max, inr_max, sodium_min,
creatinine_score, sodium_score, bilirubin_score, inr_score,
CASE
WHEN (creatinine_score + bilirubin_score + inr_score) > 4
THEN 40.0
ELSE ROUND(TRY_CAST(creatinine_score + bilirubin_score + inr_score AS DECIMAL), 1) * 10
END AS meld_initial
FROM score
)
SELECT
subject_id, hadm_id, stay_id
, CASE
WHEN meld_initial > 11
THEN meld_initial + 1.32 * sodium_score - 0.033 * meld_initial * sodium_score
ELSE meld_initial
END AS meld
FROM score2
;
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.
- 11d ago First seen · 94 lines · 0 tokens per session scan A 323d153955c2
mimic-meld-24h-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 839 tokens. A static security scan graded it A with 0 findings. It is 100% identical to mimic-apsiii-24h-raw, differing in 963 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…