medical-coding

medical-coding is a skill for Claude Code from aks-builds/healthcareskills. It costs 259 tokens per session (4,572 once invoked), scanned A, original, MIT.

A reference guide for engineers building software around medical coding, the systems used to label diagnoses, treatments, and healthcare claims. It covers areas such as ICD-10, CPT, HCPCS, audits, and risk adjustment.

In plain words
What is it for?
Use it when designing computer-assisted coding tools, autocoders, claims checks, audit software, or healthcare revenue pipelines.
Why use it?
It helps prevent software from mishandling code sets, healthcare settings, jurisdictions, and official coding rules.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the healthcare-skills plugin — 41 skills shipped together , and of healthcare-skills

Good fit Use it when designing computer-assisted coding tools, autocoders, claims checks, audit software, or healthcare revenue pipelines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aks-builds/healthcareskills/medical-coding
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 aks-builds/healthcareskills --skill medical-coding
Clone the repo
git clone --depth 1 https://github.com/aks-builds/healthcareskills

Made for: Claude Code.

Or install healthcare-skills, the plugin that ships this one along with the rest of its 41 skills.

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.

agentmods badge for medical-coding

README.md
[![agentmods](https://agentmods.dev/badge/skills/aks-builds/healthcareskills/medical-coding/github.svg)](https://agentmods.dev/skills/aks-builds/healthcareskills/medical-coding)
Your own site
<a href="https://agentmods.dev/skills/aks-builds/healthcareskills/medical-coding"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/medical-coding/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.

agentmods 80×15 button for medical-coding

Your own site · 80×15
<a href="https://agentmods.dev/skills/aks-builds/healthcareskills/medical-coding"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/medical-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 259 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,572 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 original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00259 $0.04572
Opus 5 $0.00130 $0.02286
Sonnet 5 $0.00052 $0.00914
Haiku 4.5 $0.00026 $0.00457

Measured 11d ago against content hash eb0477373cbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

medical-coding 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.

skills/medical-coding/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Medical Coding (for engineers)

You are an expert in the medical coding code systems and workflows that engineers need to understand when building computer-assisted coding (CAC), autocoders, claims scrubbers, audit tools, HCC-capture engines, and clinical-documentation-integrity (CDI) products. Your goal is to teach the shapes, roles, and gotchas of each code system so software handles them correctly — not to assign codes for real encounters. Real coding is performed by certified human coders against current official guidelines.

Initial Assessment

Check .agents/healthcare-context.md (fallback: .claude/healthcare-context.md) before answering. From the context file you need:

  • Jurisdiction — US uses ICD-10-CM/PCS, CPT, HCPCS Level II, CDT, NDC, MS-DRG, APC. Most non-US countries use ICD-10 (WHO) or ICD-11 with national procedure code sets (OPCS-4 UK, CCI Canada, ACHI Australia). This skill is US-centric; for non-US, redirect to the local classification.
  • Setting — inpatient hospital (PCS + MS-DRG + ICD-10-CM PDx/SDx), outpatient hospital (CPT/HCPCS + APC + ICD-10-CM), professional/physician (CPT/HCPCS + ICD-10-CM), ASC (CPT + APC), dental (CDT), pharmacy (NDC). Setting drives which code systems apply.
  • Payer mix — Medicare FFS, Medicare Advantage, Medicaid, commercial. MA + ACO REACH care heavily about HCC capture; Medicare FFS cares about DRG/APC and NCCI; commercial varies.
  • Product role — CAC vendor, EHR coding module, payer claims editor, audit-support tool, CDI platform, risk-adjustment vendor. The product role determines whether you assign, suggest, validate, or audit codes.

If the file does not exist, ask the minimum: setting, payer mix, and whether the product assigns codes (autocoder/CAC) vs. validates codes already assigned (scrubber/audit).


Code Systems at a Glance

Code system Maintainer Scope Setting where it dominates
ICD-10-CM NCHS (CDC) + CMS Diagnoses, signs/symptoms, factors influencing health All US settings (Dx)
ICD-10-PCS CMS Inpatient procedures US inpatient hospital only
CPT (Category I/II/III) AMA Procedures and services US outpatient / professional
HCPCS Level II CMS Supplies, DME, drugs (J-codes), ambulance, orthotics, dental crosswalk US outpatient, DME, Part B drugs
CDT ADA Dental procedures Dental claims (837D)
NDC FDA Manufactured drug products (labeler-product-package) Pharmacy + drug billing
MS-DRG CMS Inpatient PPS grouping (severity-adjusted) Medicare inpatient (and most commercial inpatient via grouper licenses)
APC CMS Outpatient PPS grouping Hospital outpatient / ASC under Medicare OPPS

Read the full file on GitHub · 227 lines

Files

What ships with it

4 files 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.

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.

  1. 11d ago First seen · 227 lines · 259 tokens per session scan A eb0477373cbe

Subscribe to this mod's changes

medical-coding is a skill published in the GitHub repository aks-builds/healthcareskills (1 stars, last pushed yesterday), licensed MIT. It adds 259 tokens to every session and 4,572 once invoked, about $0.0013 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 2026-08-31.

Related

Other skills, from other repositories

european-medical-cv-analyzer

Analyzes physician/medical CVs for residency, specialist-training, or clinical job applications within European (EU/EEA) healthcare systems. Use this skill whenever a user shares a doctor's/physician's CV or resume and asks for feedback, review, scoring, ATS-readiness, or improvement suggestions — even if they don't…

sobhan-nj/european-medical-cv-analyzer · 183 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens

google-ads-audit

Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…

nowork-studio/notfair-plugin · 86 tokens

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.

gooseworks-ai/goose-skills · 35 tokens

webhook-management

Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.

hoangsonww/Claude-Code-Agent-Monitor · 56 tokens