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.
npx skills add iblai/medical-healthcare-agents --skill epic-fhirgit clone --depth 1 https://github.com/iblai/medical-healthcare-agentsWrote 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/iblai/medical-healthcare-agents/epic-fhir)<a href="https://agentmods.dev/skills/iblai/medical-healthcare-agents/epic-fhir"><img src="https://agentmods.dev/badge/skills/iblai/medical-healthcare-agents/epic-fhir/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/iblai/medical-healthcare-agents/epic-fhir"><img src="https://agentmods.dev/badge/skills/iblai/medical-healthcare-agents/epic-fhir.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 | $0.00045 | $0.00690 |
| Opus 5.5 | $0.00018 | $0.00276 |
| Sonnet 5.5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
epic-fhir 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 2mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epic FHIR R4
What it is
Epic is the dominant EHR platform in US health systems. Its FHIR R4 API (via SMART on FHIR / backend service auth) exposes standardized clinical resources — Patient, Encounter, Condition, MedicationRequest, Observation, DocumentReference, ServiceRequest, and more. Agents use it to read encounter context, surface patient data, and (with write scopes) create draft notes or referral orders for clinician review.
When to use this skill
- Retrieve active diagnoses, medications, allergies, or lab results for clinical decision support
- Read encounter context (admit date, service type, attending provider) before routing a request
- Fetch or draft clinical documentation (DocumentReference) via the In-Basket workflow
- Create or check referral orders (ServiceRequest) during care coordination
- Access care plan activities or discharge instructions (CarePlan) for patient education
Credentials
This skill authenticates using variables declared in the metadata above. Copy ~/.openclaw/.env.example to ~/.openclaw/.env and fill in real values. Required variables:
EPIC_FHIR_BASE_URL- FHIR R4 base endpoint (e.g.,https://fhir.epicinstance.org/api/FHIR/R4)EPIC_CLIENT_ID- OAuth 2.0 client ID registered in Epic App OrchardEPIC_PRIVATE_KEY_PATH- path to RSA private key used for JWT client assertion (backend service auth)EPIC_SCOPE- space-separated SMART scopes (e.g.,system/Patient.read system/Observation.read)
Key operations
GET /Patient/{id}— demographics, MRN, language preferenceGET /Encounter?patient={id}— encounter list with class, service type, statusGET /Condition?patient={id}&clinical-status=active— active problem listGET /MedicationRequest?patient={id}&status=active— current medicationsGET /Observation?patient={id}&category=laboratory— lab results with LOINC codesGET /DocumentReference?patient={id}&type={LOINC}— clinical notes by typePOST /ServiceRequest— create referral order (write scope required)POST /DocumentReference— submit draft note to In-Basket (write scope required)
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.
- 2mo ago First seen · 42 lines · 45 tokens per session scan A cc00d0bc7c35
epic-fhir is a skill published in the GitHub repository iblai/medical-healthcare-agents (10 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 690 once invoked, about $0.0002 per session on Opus 5.5. 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.
epic-fhir compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| epic-fhiriblai/medical-healthcare-agents | Skill | 10 | 5mo ago | MIT | A | 45 | Claude Code, Codex |
| architecture-patternswshobson/agents | Skill | 42k | yesterday | MIT | A | 65 | Claude Code |
| saga-orchestrationwshobson/agents | Skill | 42k | yesterday | MIT | A | 91 | Claude Code |
| fastapi-templateswshobson/agents | Skill | 42k | yesterday | MIT | A | 37 | Claude Code |
| event-store-designwshobson/agents | Skill | 42k | yesterday | MIT | A | 33 | Claude Code |
| error-handling-patternswshobson/agents | Skill | 42k | yesterday | MIT | A | 43 | Claude Code |
| api-design-principleswshobson/agents | Skill | 42k | yesterday | MIT | A | 44 | Claude Code |