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 langcare/langcare-mcp-fhir --skill referral-generatorgit clone --depth 1 https://github.com/langcare/langcare-mcp-fhirWrote 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/langcare/langcare-mcp-fhir/referral-generator)<a href="https://agentmods.dev/skills/langcare/langcare-mcp-fhir/referral-generator"><img src="https://agentmods.dev/badge/skills/langcare/langcare-mcp-fhir/referral-generator/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/langcare/langcare-mcp-fhir/referral-generator"><img src="https://agentmods.dev/badge/skills/langcare/langcare-mcp-fhir/referral-generator.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 | $0.00098 | $0.03390 |
| Opus 5.5 | $0.00039 | $0.01356 |
| Sonnet 5.5 | $0.00020 | $0.00678 |
| Haiku 4.5 | $0.00010 | $0.00339 |
Grade A, and why
referral-generator 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral Generator
Overview
Generate a complete specialist referral as a FHIR ServiceRequest resource. Automatically populate the referral with relevant clinical context: active conditions as the reason for referral, pertinent lab results, current medications, and imaging findings. Flag conditions commonly requiring prior authorization. Format the clinical question for the specialist based on referral indication.
FHIR Resources Used
| Resource | Purpose | Key Fields |
|---|---|---|
| ServiceRequest | The referral itself | status, intent, code, reasonReference, supportingInfo, note |
| Condition | Reason for referral | code, clinicalStatus, onsetDateTime |
| Observation | Supporting lab/vital data | code, valueQuantity, effectiveDateTime, interpretation |
| DiagnosticReport | Imaging and pathology findings | code, conclusion, presentedForm |
| MedicationRequest | Current medications relevant to specialty | medicationCodeableConcept, dosageInstruction, status |
| MedicationStatement | Patient-reported medications | medicationCodeableConcept, status |
| Patient | Demographics and insurance | name, birthDate, gender, identifier |
| Coverage | Insurance for prior auth determination | type, payor, class |
| Procedure | Prior relevant procedures | code, performedDateTime, status |
Instructions
Step 1: Identify Patient and Referral Target
Confirm patient identity:
Tool: fhir_read
resourceType: "Patient"
id: "[patient-id]"
Extract: name, DOB, gender, MRN (from identifier where type.coding.code = "MR").
Step 2: Gather Active Conditions
Tool: fhir_search
resourceType: "Condition"
queryParams: "patient=[patient-id]&clinical-status=active"
Identify the primary reason for referral from the user's request. Match it to an active Condition. If no matching Condition exists, the referral can still proceed but note that the referring diagnosis should be documented.
Step 3: Retrieve Relevant Lab Results
Based on the target specialty, search for pertinent labs. Use specialty-specific LOINC codes from references/referral-indications.md.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 322 lines · 98 tokens per session scan A f4fb72c8c429
referral-generator is a skill published in the GitHub repository langcare/langcare-mcp-fhir (71 stars, last pushed 6mo ago), licensed MIT. It adds 98 tokens to every session and 3,390 once invoked, about $0.0004 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 2026-08-30.
referral-generator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| referral-generatorlangcare/langcare-mcp-fhir | Skill | 71 | 6mo ago | MIT | A | 98 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| ppt-reviewOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 2 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |