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/healthex-export-redactedWrote 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/healthex-export-redacted)<a href="https://agentmods.dev/skills/aks129/healthclawguardrails/healthex-export-redacted"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/healthex-export-redacted/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/healthex-export-redacted"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/healthex-export-redacted.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 Privilege Escalation · line 34 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 19 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00149 | $0.01335 |
| Opus 5 | $0.00075 | $0.00668 |
| Sonnet 5 | $0.00030 | $0.00267 |
| Haiku 4.5 | $0.00015 | $0.00134 |
Grade A, and why
healthex-export-redacted scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HealthEx Export (MCP, Redacted)
scripts/export_healthex_mcp.py is the current HealthEx pull path. It:
- Opens a Streamable HTTP MCP session to
https://api.healthex.io/mcp - Optionally calls
update_records+check_records_statusto refresh - Invokes each clinical tool (
get_health_summary,get_conditions,get_medications,get_allergies,get_immunizations,get_vitals,get_labs,get_procedures,get_visits,search_clinical_notes) - Redacts PHI in-process before anything touches disk — via
scripts/healthclaw_redact.py, which mirrors the HealthClaw guardrail proxy's redaction rules - Writes the result as JSON (default) or NDJSON (one resource per line)
The raw MCP response is never written. Only the redacted payload goes to disk.
Quick Start
# Set the HealthEx token (use macOS Keychain on the Mac mini)
export HEALTHEX_AUTH_TOKEN="$(security find-generic-password -s healthex -w)"
# Default — all tools, local redaction, single JSON file
python scripts/export_healthex_mcp.py \
--tenant-id my-tenant \
--output exports/healthex-$(date +%Y-%m-%d).json
# NDJSON (one line per FHIR resource — easier to diff / grep)
python scripts/export_healthex_mcp.py \
--tenant-id my-tenant \
--output exports/healthex-$(date +%Y-%m-%d).ndjson
# Only the tools you need
python scripts/export_healthex_mcp.py \
--tenant-id my-tenant \
--output exports/labs-only.json \
--tools get_labs get_conditions
# Proxy mode — redact via a running HealthClaw guardrail server instead
python scripts/export_healthex_mcp.py \
--tenant-id my-tenant \
--output exports/snap.json \
--redact-mode proxy \
--healthclaw-url https://healthclaw.io
# Synthetic-only escape hatch (keeps PHI in output — NEVER use on real data)
python scripts/export_healthex_mcp.py \
--tenant-id desktop-demo \
--output exports/demo-raw.json \
--no-redact
Redaction Rules (identical to the HealthClaw proxy)
| Field | Rule |
|---|---|
HumanName.given / family / text |
Collapsed to initials ("E. V.") |
Address.line / city / postalCode |
Dropped (state + country kept) |
Identifier.value (MRN, member, subscriber) |
SHA-256, optional HEALTHCLAW_REDACT_SALT |
birthDate |
Truncated to YYYY |
telecom[].value (phone / email / fax / sms) |
Replaced with "***" |
Patient.photo |
Removed entirely |
text.div narrative |
Emptied |
note[] (Condition / Observation / …) |
Emptied |
| Generic flat-dict PHI keys (ssn, dob, …) | Wiped at any nesting depth |
code.coding, valueQuantity, dates |
Preserved — clinical signal intact |
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.
- 12d ago First seen · 115 lines · 149 tokens per session scan A 3b11949653fc
healthex-export-redacted is a skill published in the GitHub repository aks129/HealthClawGuardrails (30 stars, last pushed today), licensed MIT. It adds 149 tokens to every session and 1,335 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.
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…