What is mimic-charlson-raw?

Reference SQL for calculating the Charlson Comorbidity Index, a healthcare score that summarizes a patient’s existing illnesses using diagnosis codes.

Use it to calculate comorbidity scores for hospital admissions or prepare patient groups for healthcare research and outcome analysis.

It provides a standard query for turning ICD-9 and ICD-10 hospital diagnoses into weighted comorbidity and age scores.

mimic-charlson-raw — Skill for Claude Code and Codex by hannesill

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-charlson-raw

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hannesill/m4/mimic-charlson-raw/github.svg)](https://agentmods.dev/skills/hannesill/m4/mimic-charlson-raw)

Your own site

<a href="https://agentmods.dev/skills/hannesill/m4/mimic-charlson-raw"><img src="https://agentmods.dev/badge/skills/hannesill/m4/mimic-charlson-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hannesill/m4/mimic-charlson-raw"><img src="https://agentmods.dev/badge/skills/hannesill/m4/mimic-charlson-raw.svg" alt="Reviewed on agentmods" width="80" 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 3,623 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.03623
Opus 5	$0.00000	$0.01811
Sonnet 5	$0.00000	$0.00725
Haiku 4.5	$0.00000	$0.00362

Measured 10d ago against content hash 0b976dd00710, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mimic-charlson-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 10d 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 — 1,115 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/charlson/mimic-charlson-raw/skills-rawsql/mimic-charlson-raw/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 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: Charlson Comorbidity Index
-- Calculates the Charlson Comorbidity Index (CCI) for each hospital
-- admission using ICD-9 and ICD-10 diagnosis codes. Includes 17
-- comorbidity conditions with original Charlson weights and age score.
-- ------------------------------------------------------------------

-- Reference:
--    Charlson ME et al. "A new method of classifying prognostic
--    comorbidity in longitudinal studies." J Chronic Dis. 1987;40(5):373-83.

-- ICD mapping reference:
--    Quan H et al. "Coding algorithms for defining comorbidities in
--    ICD-9-CM and ICD-10 administrative data." Med Care. 2005;43(11):1130-9.

-- Adapted from mimic-code charlson.sql

WITH diag AS (
  SELECT
    hadm_id,
    CASE WHEN icd_version = 9 THEN icd_code ELSE NULL END AS icd9_code,
    CASE WHEN icd_version = 10 THEN icd_code ELSE NULL END AS icd10_code
  FROM mimiciv_hosp.diagnoses_icd
), com AS (
  SELECT
    ad.hadm_id,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) IN ('410', '412')
        OR SUBSTR(icd10_code, 1, 3) IN ('I21', 'I22')
        OR SUBSTR(icd10_code, 1, 4) = 'I252'
        THEN 1
        ELSE 0
      END
    ) AS myocardial_infarct,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) = '428'
        OR SUBSTR(icd9_code, 1, 5) IN ('39891', '40201', '40211', '40291', '40401', '40403', '40411', '40413', '40491', '40493')
        OR SUBSTR(icd9_code, 1, 4) BETWEEN '4254' AND '4259'
        OR SUBSTR(icd10_code, 1, 3) IN ('I43', 'I50')
        OR SUBSTR(icd10_code, 1, 4) IN ('I099', 'I110', 'I130', 'I132', 'I255', 'I420', 'I425', 'I426', 'I427', 'I428', 'I429', 'P290')
        THEN 1
        ELSE 0
      END
    ) AS congestive_heart_failure,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) IN ('440', '441')
        OR SUBSTR(icd9_code, 1, 4) IN ('0930', '4373', '4471', '5571', '5579', 'V434')
        OR SUBSTR(icd9_code, 1, 4) BETWEEN '4431' AND '4439'
        OR SUBSTR(icd10_code, 1, 3) IN ('I70', 'I71')
        OR SUBSTR(icd10_code, 1, 4) IN ('I731', 'I738', 'I739', 'I771', 'I790', 'I792', 'K551', 'K558', 'K559', 'Z958', 'Z959')
        THEN 1
        ELSE 0
      END
    ) AS peripheral_vascular_disease,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) BETWEEN '430' AND '438'
        OR SUBSTR(icd9_code, 1, 5) = '36234'
        OR SUBSTR(icd10_code, 1, 3) IN ('G45', 'G46')
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'I60' AND 'I69'
        OR SUBSTR(icd10_code, 1, 4) = 'H340'
        THEN 1
        ELSE 0
      END
    ) AS cerebrovascular_disease,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) = '290'
        OR SUBSTR(icd9_code, 1, 4) IN ('2941', '3312')
        OR SUBSTR(icd10_code, 1, 3) IN ('F00', 'F01', 'F02', 'F03', 'G30')
        OR SUBSTR(icd10_code, 1, 4) IN ('F051', 'G311')
        THEN 1
        ELSE 0
      END
    ) AS dementia,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) BETWEEN '490' AND '505'
        OR SUBSTR(icd9_code, 1, 4) IN ('4168', '4169', '5064', '5081', '5088')
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'J40' AND 'J47'
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'J60' AND 'J67'
        OR SUBSTR(icd10_code, 1, 4) IN ('I278', 'I279', 'J684', 'J701', 'J703')
        THEN 1
        ELSE 0
      END
    ) AS chronic_pulmonary_disease,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) = '725'
        OR SUBSTR(icd9_code, 1, 4) IN ('4465', '7100', '7101', '7102', '7103', '7104', '7140', '7141', '7142', '7148')
        OR SUBSTR(icd10_code, 1, 3) IN ('M05', 'M06', 'M32', 'M33', 'M34')
        OR SUBSTR(icd10_code, 1, 4) IN ('M315', 'M351', 'M353', 'M360')
        THEN 1
        ELSE 0
      END
    ) AS rheumatic_disease,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) IN ('531', '532', '533', '534')
        OR SUBSTR(icd10_code, 1, 3) IN ('K25', 'K26', 'K27', 'K28')
        THEN 1
        ELSE 0
      END
    ) AS peptic_ulcer_disease,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) IN ('570', '571')
        OR SUBSTR(icd9_code, 1, 4) IN ('0706', '0709', '5733', '5734', '5738', '5739', 'V427')
        OR SUBSTR(icd9_code, 1, 5) IN ('07022', '07023', '07032', '07033', '07044', '07054')
        OR SUBSTR(icd10_code, 1, 3) IN ('B18', 'K73', 'K74')
        OR SUBSTR(icd10_code, 1, 4) IN ('K700', 'K701', 'K702', 'K703', 'K709', 'K713', 'K714', 'K715', 'K717', 'K760', 'K762', 'K763', 'K764', 'K768', 'K769', 'Z944')
        THEN 1
        ELSE 0
      END
    ) AS mild_liver_disease,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 4) IN ('2500', '2501', '2502', '2503', '2508', '2509')
        OR SUBSTR(icd10_code, 1, 4) IN ('E100', 'E101', 'E106', 'E108', 'E109', 'E110', 'E111', 'E116', 'E118', 'E119', 'E120', 'E121', 'E126', 'E128', 'E129', 'E130', 'E131', 'E136', 'E138', 'E139', 'E140', 'E141', 'E146', 'E148', 'E149')
        THEN 1
        ELSE 0
      END
    ) AS diabetes_without_cc,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 4) IN ('2504', '2505', '2506', '2507')
        OR SUBSTR(icd10_code, 1, 4) IN ('E102', 'E103', 'E104', 'E105', 'E107', 'E112', 'E113', 'E114', 'E115', 'E117', 'E122', 'E123', 'E124', 'E125', 'E127', 'E132', 'E133', 'E134', 'E135', 'E137', 'E142', 'E143', 'E144', 'E145', 'E147')
        THEN 1
        ELSE 0
      END
    ) AS diabetes_with_cc,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) IN ('342', '343')
        OR SUBSTR(icd9_code, 1, 4) IN ('3341', '3440', '3441', '3442', '3443', '3444', '3445', '3446', '3449')
        OR SUBSTR(icd10_code, 1, 3) IN ('G81', 'G82')
        OR SUBSTR(icd10_code, 1, 4) IN ('G041', 'G114', 'G801', 'G802', 'G830', 'G831', 'G832', 'G833', 'G834', 'G839')
        THEN 1
        ELSE 0
      END
    ) AS paraplegia,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) IN ('582', '585', '586', 'V56')
        OR SUBSTR(icd9_code, 1, 4) IN ('5880', 'V420', 'V451')
        OR SUBSTR(icd9_code, 1, 4) BETWEEN '5830' AND '5837'
        OR SUBSTR(icd9_code, 1, 5) IN ('40301', '40311', '40391', '40402', '40403', '40412', '40413', '40492', '40493')
        OR SUBSTR(icd10_code, 1, 3) IN ('N18', 'N19')
        OR SUBSTR(icd10_code, 1, 4) IN ('I120', 'I131', 'N032', 'N033', 'N034', 'N035', 'N036', 'N037', 'N052', 'N053', 'N054', 'N055', 'N056', 'N057', 'N250', 'Z490', 'Z491', 'Z492', 'Z940', 'Z992')
        THEN 1
        ELSE 0
      END
    ) AS renal_disease,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) BETWEEN '140' AND '172'
        OR SUBSTR(icd9_code, 1, 4) BETWEEN '1740' AND '1958'
        OR SUBSTR(icd9_code, 1, 3) BETWEEN '200' AND '208'
        OR SUBSTR(icd9_code, 1, 4) = '2386'
        OR SUBSTR(icd10_code, 1, 3) IN ('C43', 'C88')
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'C00' AND 'C26'
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'C30' AND 'C34'
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'C37' AND 'C41'
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'C45' AND 'C58'
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'C60' AND 'C76'
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'C81' AND 'C85'
        OR SUBSTR(icd10_code, 1, 3) BETWEEN 'C90' AND 'C97'
        THEN 1
        ELSE 0
      END
    ) AS malignant_cancer,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 4) IN ('4560', '4561', '4562')
        OR SUBSTR(icd9_code, 1, 4) BETWEEN '5722' AND '5728'
        OR SUBSTR(icd10_code, 1, 4) IN ('I850', 'I859', 'I864', 'I982', 'K704', 'K711', 'K721', 'K729', 'K765', 'K766', 'K767')
        THEN 1
        ELSE 0
      END
    ) AS severe_liver_disease,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) IN ('196', '197', '198', '199')
        OR SUBSTR(icd10_code, 1, 3) IN ('C77', 'C78', 'C79', 'C80')
        THEN 1
        ELSE 0
      END
    ) AS metastatic_solid_tumor,
    MAX(
      CASE
        WHEN SUBSTR(icd9_code, 1, 3) IN ('042', '043', '044')
        OR SUBSTR(icd10_code, 1, 3) IN ('B20', 'B21', 'B22', 'B24')
        THEN 1
        ELSE 0
      END
    ) AS aids
  FROM mimiciv_hosp.admissions AS ad
  LEFT JOIN diag
    ON ad.hadm_id = diag.hadm_id
  GROUP BY
    ad.hadm_id
), ag AS (
  SELECT
    hadm_id,
    age,
    CASE
      WHEN age <= 50
      THEN 0
      WHEN age <= 60
      THEN 1
      WHEN age <= 70
      THEN 2
      WHEN age <= 80
      THEN 3
      ELSE 4
    END AS age_score
  FROM mimiciv_derived.age
)
SELECT
  ad.subject_id,
  ad.hadm_id,
  ag.age_score,
  myocardial_infarct,
  congestive_heart_failure,
  peripheral_vascular_disease,
  cerebrovascular_disease,
  dementia,
  chronic_pulmonary_disease,
  rheumatic_disease,
  peptic_ulcer_disease,
  mild_liver_disease,
  diabetes_without_cc,
  diabetes_with_cc,
  paraplegia,
  renal_disease,
  malignant_cancer,
  severe_liver_disease,
  metastatic_solid_tumor,
  aids,
  age_score + myocardial_infarct + congestive_heart_failure + peripheral_vascular_disease + cerebrovascular_disease + dementia + chronic_pulmonary_disease + rheumatic_disease + peptic_ulcer_disease + GREATEST(mild_liver_disease, 3 * severe_liver_disease) + GREATEST(2 * diabetes_with_cc, diabetes_without_cc) + GREATEST(2 * malignant_cancer, 6 * metastatic_solid_tumor) + 2 * paraplegia + 2 * renal_disease + 6 * aids AS charlson_comorbidity_index
FROM mimiciv_hosp.admissions AS ad
LEFT JOIN com
  ON ad.hadm_id = com.hadm_id
LEFT JOIN ag
  ON com.hadm_id = ag.hadm_id

Read the full file on GitHub · 258 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.

10d ago First seen · 258 lines · 0 tokens per session scan A 0b976dd00710

Subscribe to this mod's changes

mimic-charlson-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 3,623 tokens. A static security scan graded it A with 0 findings. It is 100% identical to mimic-apsiii-24h-raw, differing in 1,115 lines, and is treated as a copy.

Autonomous Agents Scientific agents clinical-data clinical-research code-execution mcp

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

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…

earthtojake/text-to-cad · 111 tokens

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…

mims-harvard/ToolUniverse · 82 tokens

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…

mims-harvard/ToolUniverse · 155 tokens

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…

mims-harvard/ToolUniverse · 100 tokens

tooluniverse-pharmacogenomics

Pharmacogenomics (PGx) research — drug-gene interactions (CPIC, PharmGKB), CPIC dosing guidelines, variant-drug-response associations, ethnic-allele-frequency considerations, and metabolizer-status scoring. Use for PGx-informed dosing recommendations, CYP/HLA pharmacogenomic allele interpretation, and…

mims-harvard/ToolUniverse · 80 tokens