Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aks129/HealthClawGuardrailsnpx agentmods add skills/aks129/healthclawguardrails/getting-startedWrote 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/aks129/healthclawguardrails/getting-started)<a href="https://agentmods.dev/skills/aks129/healthclawguardrails/getting-started"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/getting-started/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/aks129/healthclawguardrails/getting-started"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/getting-started.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 | $0.00200 | $0.05985 |
| Opus 5 | $0.00100 | $0.02993 |
| Sonnet 5 | $0.00040 | $0.01197 |
| Haiku 4.5 | $0.00020 | $0.00598 |
Grade C, and why
getting-started scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://localhost:8080/fhir/metadata | python3 -c \ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# C — scripted installer (check openclaw.ai for the current curl URL) How it starts
The opening of the file, as written. The whole thing — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Getting started — HealthClaw + OpenClaw + your health data
The goal: a fully local, private, agent-mediated view of your own clinical records. Nothing leaves your machine unless you explicitly send it. By the end of this guide you'll have:
- An OpenClaw gateway (your local AI assistant runtime — Telegram / WhatsApp / iMessage / Slack / web)
- An open-source FHIR server holding your records (HAPI or Medplum)
- Your real EHR records pulled in via a patient-right-of-access service of your choice
- HealthClaw Guardrails sitting between any agent and that data, enforcing PHI redaction, audit trails, step-up auth, and tenant isolation
- OpenClaw agent personas (Sally-PCP, Mary-pharmacy, Dom-fitness, Kristy-scheduler) already wired to the slash-command surface and aware of every HealthClaw tool
If you already have one or more of these, the guide will tell you how to verify and skip ahead — don't reinstall what's working.
Privacy guarantee. Steps 1–4 keep your raw clinical data on your machine. The only network calls are to your chosen EHR connector (HealthEx, Flexpa, etc.) and that traffic is OAuth/SMART-on-FHIR with your explicit consent. PHI is redacted in-process before any file is written.
Prerequisites
| Requirement | Why | How to check |
|---|---|---|
| macOS / Linux | Stack is tested on Darwin + Linux. Windows works under WSL2. | uname -sm |
| Python 3.11+ | Flask app + scripts | python3 --version |
| Node 22+ | OpenClaw + the MCP orchestrator | node --version |
| Docker (optional) | Easiest way to run HAPI / Medplum / HealthClaw | docker --version |
git |
All repos | git --version |
| ~30 min | First-time setup | — |
If anything is missing, install via Homebrew (macOS) or your distro's package manager. Don't proceed until all four exist.
Step 1a — OpenClaw
OpenClaw is the local AI gateway: it runs your agent personas, exposes them on whichever channels you want (Telegram, WhatsApp, iMessage, Slack, web), and gives them access to your installed skills.
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 · 614 lines · 200 tokens per session scan C b1932aeabc6e
getting-started is a skill published in the GitHub repository aks129/HealthClawGuardrails (30 stars, last pushed today), licensed MIT. It adds 200 tokens to every session and 5,985 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
healthcare-fhir
Design RESTful clinical data exchanges using HL7 FHIR standards.
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.
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.
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).…
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.
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…