agentleFS
aks129aks129/HealthClawGuardrails/skills/fhir-r6-guardrails/SKILL.md

fhir-r6-guardrails

Skill33 starsChanged 4 months agoMITView on GitHub

HealthClaw Guardrails (healthclaw.io) — FHIR agent guardrails for clinical data access via MCP. Supports FHIR R4 US Core v9 (stable) and FHIR R6 ballot3 (experimental). Use when: (1) Reading patient data through MCP tools with automatic PHI redaction, (2) Writing clinical resources with two-phase propose/commit and step-up authorization, (3) Querying observation statistics or recent lab results, (4) Evaluating R6 Permission resources for access control decisions, (5) Auditing agent access to healthcare data. 14 MCP tools.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Propose: Call fhir.propose_write with the resource and operation (create/update).

    line 60
  2. Distinctive:

    Review: Check the proposal response:

    line 63
  3. Very specific:

    Commit: Call fhir.commit_write with the same resource.

    line 68
  4. Distinctive:

    Not supported in local mode: chaining, _include, _revinclude, modifiers.

    line 123
  5. Distinctive:

    No historical versioning (version_id increments but old versions not retrievable)

    line 152

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

HealthClaw Guardrails

A healthclaw.io open source project. Reference implementation of security and compliance patterns for AI agent access to FHIR data via MCP.

Supports FHIR R4 US Core v9 (stable) and FHIR R6 v6.0.0-ballot3 (experimental).

This is a runtime guardrail layer, not a knowledge skill. It sits between any AI agent and FHIR data (local or upstream), enforcing PHI redaction, audit trails, step-up authorization, and tenant isolation on every request.

When to Use This Skill

  • You need to read, search, or write FHIR clinical resources through MCP
  • You need PHI to be automatically redacted before the agent sees it
  • You need an immutable audit trail of all agent access
  • You need step-up authorization gates on write operations
  • You need to evaluate R6 Permission resources for access control

MCP Tools Available (12)

Read Tools (no step-up required)

ToolPurpose
context.getRetrieve a pre-built context envelope with patient-centric resources
fhir.readRead a single FHIR resource by type and ID (auto-redacted)
fhir.searchSearch resources with patient, code, status, date filters
fhir.validateStructural validation of a proposed resource
fhir.statsObservation statistics: count, min, max, mean over valueQuantity
fhir.lastnMost recent N observations per code
fhir.permission_evaluateEvaluate R6 Permission for permit/deny with reasoning
fhir.subscription_topicsList available SubscriptionTopics
curatr.evaluateEvaluate a FHIR resource for data quality issues

Write Tools (require step-up token)

ToolPurpose
fhir.propose_writeValidate and preview a write without committing
fhir.commit_writeCommit a proposed write (requires X-Step-Up-Token)
curatr.apply_fixApply patient-approved data quality fixes with Provenance

Two-Phase Write Pattern

Writes always follow propose-then-commit:

  1. Propose: Call fhir.propose_write with the resource and operation (create/update). This validates the resource and returns a preview. No data is changed.
  2. Review: Check the proposal response:
    • proposal_status: "ready" means validation passed
    • requires_human_confirmation: true for clinical resource types
    • requires_step_up: true always for commits
  3. Commit: Call fhir.commit_write with the same resource. Include:
    • X-Step-Up-Token header (HMAC-SHA256 signed, 5-minute TTL)
    • For clinical resources, a 428 means a human must confirm. Stop and tell the person; never set X-Human-Confirmed yourself. Outward actions (calls, texts, forms) go through the action rail's out-of-band approval.

Clinical Resource Types (require human-in-the-loop)

Observation, Condition, MedicationRequest, DiagnosticReport, AllergyIntolerance, Procedure, CarePlan, Immunization, NutritionIntake, DeviceAlert.

Supported FHIR Resource Types

FHIR R4 US Core v9 (Stable)

Patient, Encounter, Observation, AuditEvent, Consent, Condition, Provenance, AllergyIntolerance, Immunization, MedicationRequest, Medication, MedicationDispense, Procedure, DiagnosticReport, CarePlan, CareTeam, Goal, DocumentReference, Location, Organization, Practitioner, PractitionerRole, RelatedPerson, Coverage, ServiceRequest, Specimen, FamilyMemberHistory.

FHIR R6 ballot3 (Experimental)

Permission, SubscriptionTopic, Subscription, NutritionIntake, NutritionProduct, DeviceAlert, DeviceAssociation, Requirements, ActorDefinition.

  • Permission — Access control (separate from Consent). $evaluate operation.
  • DeviceAlert — ISO/IEEE 11073 device alarms.
  • NutritionIntake — Dietary consumption tracking.
  • DeviceAssociation, NutritionProduct, Requirements, ActorDefinition — CRUD only.

Security Guardrails (Always Active)

PHI Redaction

Applied on every read path. Names truncated to initials, identifier values removed (system and type kept), addresses stripped to city/state/country, birth dates truncated to year, photos removed, notes replaced with [Redacted].

Audit Trail

Append-only AuditEvent records for every resource access. Database-level immutability. Logs agent ID, tenant ID, resource accessed, and outcome.

Step-Up Authorization

HMAC-SHA256 tokens with 128-bit nonce, 5-minute TTL, tenant binding. Required for all write operations.

Tenant Isolation

X-Tenant-Id header enforced on every query at the database layer.

Search Parameters (Local Mode)

Supported: patient (reference), code (token), status (token), _lastUpdated (date with ge/le/gt/lt prefix), _count (1-200), _sort (_lastUpdated/-_lastUpdated), _summary (count).

Not supported in local mode: chaining, _include, _revinclude, modifiers.

In upstream proxy mode, all query parameters are forwarded to the upstream server.

Setup

# Docker Compose (recommended)
docker-compose up -d --build

# Manual
uv sync && python main.py &
cd services/agent-orchestrator && npm ci && npm start

Required environment variables:

  • STEP_UP_SECRET — HMAC secret for step-up tokens

Optional:

Known Limitations

  • Local mode uses SQLite JSON blob storage (not indexed search)
  • Structural validation only (no StructureDefinition or terminology binding)
  • SubscriptionTopic stored but notifications not dispatched
  • Human-in-the-loop is header-based, not cryptographic
  • No historical versioning (version_id increments but old versions not retrievable)
  • Upstream proxy: no response caching, no cross-version translation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.