curatr

curatr is a skill for Claude Code from aks129/HealthClawGuardrails. It costs 148 tokens per session (1,929 once invoked), scanned A, original, MIT.

A patient-facing checker for FHIR R4 health records. FHIR is a standard format for exchanging medical data, and the checker explains coding and record-quality problems in plain language.

In plain words
What is it for?
Use it to inspect supported conditions, allergies, medications, immunizations, procedures, and diagnostic reports, including their medical codes, statuses, links, and dates.
Why use it?
It helps patients spot outdated, invalid, or incomplete information that may affect how their care history is represented. It also lets them decide whether to correct their record or ask a provider to fix it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for openclaw.

Part of the healthclaw-guardrails plugin — 14 skills, 3 MCP servers shipped together

Good fit Use it to inspect supported conditions, allergies, medications, immunizations, procedures, and diagnostic reports, including their medical codes, statuses, links, and dates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aks129/healthclawguardrails/curatr
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 aks129/HealthClawGuardrails --skill curatr
Clone the repo
git clone --depth 1 https://github.com/aks129/HealthClawGuardrails

Made for: Claude Code.

Or install healthclaw-guardrails, the plugin that ships this one along with the rest of its 14 skills, 3 MCP servers.

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 curatr

README.md
[![agentmods](https://agentmods.dev/badge/skills/aks129/healthclawguardrails/curatr/github.svg)](https://agentmods.dev/skills/aks129/healthclawguardrails/curatr)
Your own site
<a href="https://agentmods.dev/skills/aks129/healthclawguardrails/curatr"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/curatr/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 curatr

Your own site · 80×15
<a href="https://agentmods.dev/skills/aks129/healthclawguardrails/curatr"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/curatr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,929 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Memory Poisoning · line 186
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
  • medium Excessive Agency · line 172
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00148 $0.01929
Opus 5 $0.00074 $0.00964
Sonnet 5 $0.00030 $0.00386
Haiku 4.5 $0.00015 $0.00193

Measured 12d ago against content hash 9ba06fc1f676, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

curatr 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.

skills/curatr/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HealthClaw Curatr

A patient-facing data quality skill that evaluates FHIR health records for coding issues, presents them in plain language, and lets the patient decide how to fix them.

Your health data belongs to you. Curatr helps you understand what's in it, spot problems, and take action — whether that's correcting your personal record or requesting your provider fix the source.

Supported FHIR R4 US Core v9 Resource Types

Resource Checks
Condition ICD-9 detection, ICD-10-CM/SNOMED validity, clinicalStatus, verificationStatus
AllergyIntolerance clinicalStatus, patient link, allergen code (RxNorm/SNOMED)
MedicationRequest status, intent, medication code (RxNorm)
Immunization status, vaccineCode (CVX/SNOMED), occurrenceDateTime
Procedure status, procedure code (SNOMED/CPT)
DiagnosticReport status, report code (LOINC)

For all other resource types, Curatr runs a generic coding scan checking all coding[] elements for deprecated systems.

What Curatr Checks

Code System Quality

  • Deprecated systems: ICD-9-CM codes (retired October 2015) flagged as critical
  • Code validity: Live lookups against public terminology services — no account needed
  • Display name accuracy: Checks whether the written description matches the official term

Structural Completeness

  • Missing required fields (varies by resource type — see table above)
  • Invalid status values (e.g. unrecognized clinicalStatus codes)
  • Missing standard medical codes

Terminology Services Used (all public, no auth required)

Service Systems Validated
tx.fhir.org — HL7 public FHIR terminology server SNOMED CT, LOINC
NLM Clinical Tables API ICD-10-CM
RXNAV API RxNorm

MCP Tools

curatr.evaluate (read-only)

Evaluate a FHIR resource for data quality issues.

Input:

{
  "resource_type": "Condition",
  "resource_id": "cond-001"
}

Read the full file on GitHub · 219 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.

  1. 12d ago First seen · 219 lines · 148 tokens per session scan A 9ba06fc1f676

Subscribe to this mod's changes

curatr is a skill published in the GitHub repository aks129/HealthClawGuardrails (30 stars, last pushed today), licensed MIT. It adds 148 tokens to every session and 1,929 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

healthcare-fhir

Design RESTful clinical data exchanges using HL7 FHIR standards.

andreibesleaga/GABBE · 17 tokens

lab-report-walkthrough

Walk a person through their lab report — read the original document, organize results by panel, flag out-of-range values against the printed reference ranges, compare with their history, and explain in plain language. Use when the user uploads a lab report (PDF/image) or asks what their blood test results mean.

thetahealth/mirobody · 67 tokens

healthcare-expert

Expert-level healthcare systems, medical informatics, HIPAA compliance, and health data standards. Use when the user mentions medical, HIPAA, HL7, FHIR, or EHR, or when the task involves Healthcare IT, Standards and Protocols, Regulatory Compliance, or Security and Compliance.

personamanagmentlayer/pcl · 64 tokens

hl7gen

Use when generating, validating, or converting HL7 v2 healthcare messages, or converting HL7 v2 to FHIR. Covers synthetic test-message generation for any of 185 HL7 v2 message types across versions 2.1–2.8.2, message validation, FHIR R5/R4B conversion, and structure exploration (required/optional/repeating fields).…

mwaseem75/hl7gen · 131 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens