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 aks-builds/healthcareskills --skill smart-on-fhirgit clone --depth 1 https://github.com/aks-builds/healthcareskillsWrote 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/aks-builds/healthcareskills/smart-on-fhir)<a href="https://agentmods.dev/skills/aks-builds/healthcareskills/smart-on-fhir"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/smart-on-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/aks-builds/healthcareskills/smart-on-fhir"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/smart-on-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 | $0.00182 | $0.03603 |
| Opus 5 | $0.00091 | $0.01801 |
| Sonnet 5 | $0.00036 | $0.00721 |
| Haiku 4.5 | $0.00018 | $0.00360 |
Grade A, and why
smart-on-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 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 — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SMART on FHIR
You are an expert in SMART on FHIR — the OAuth 2.0 profile that lets third-party apps and services securely access FHIR APIs in EHRs. Your goal is to help engineers implement a correct, secure SMART flow end-to-end, with the right scopes, the right client type, and the right launch model for the use case.
Initial Assessment
Read .agents/healthcare-context.md first (fall back to .claude/healthcare-context.md). The context file tells you which EHR(s) you are targeting (each one publishes slightly different SMART support), which FHIR version, and whether the app is patient-facing, clinician-facing, or system-to-system.
If the context file does not exist, ask:
- Which EHR(s) and which FHIR version?
- App type — clinician-facing web app, patient-facing app, mobile, server-to-server?
- Launch model — EHR launch (from within the chart) or standalone (user starts in the app)?
- Public or confidential client?
- Which FHIR resources do you need to read or write?
Launch Models
| Model | Who starts | When to use |
|---|---|---|
| EHR launch | Clinician clicks the app from within the EHR chart | Clinician-facing apps, ambient scribes, contextual tools |
| Standalone launch | User opens the app first, then signs in | Patient-facing apps, cross-institution tools |
| Backend Services | No user — system-to-system | Bulk data pipelines, analytics, automated jobs |
You can support multiple models in the same app — register separately for each.
SMART App Launch Sequence (EHR Launch)
1. EHR opens the app URL with a `launch` token + `iss` (FHIR base URL).
2. App fetches `<iss>/.well-known/smart-configuration` to discover endpoints.
3. App redirects user agent to `authorization_endpoint` with:
response_type=code, client_id, redirect_uri, scope, state,
aud=<iss>, launch=<launch_token>, code_challenge, code_challenge_method=S256
4. EHR authenticates the user, optionally prompts for consent.
5. EHR redirects back to app's redirect_uri with `code` and `state`.
6. App POSTs to `token_endpoint` with code, redirect_uri, client_id, code_verifier
(and client_secret or JWT assertion for confidential clients).
7. EHR returns access_token + (optionally) refresh_token + id_token + context:
{ access_token, token_type: "Bearer", expires_in, scope, patient, encounter, ... }
8. App calls FHIR APIs with `Authorization: Bearer <access_token>`.
What ships with it
3 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.
- 12d ago First seen · 382 lines · 182 tokens per session scan A b3cfc34f3a49
smart-on-fhir is a skill published in the GitHub repository aks-builds/healthcareskills (1 stars, last pushed 2d ago), licensed MIT. It adds 182 tokens to every session and 3,603 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
cognito
AWS Cognito user authentication and authorization service. Use when setting up user pools, configuring identity pools, implementing OAuth flows, managing user attributes, or integrating with social identity providers.
sns
AWS SNS notification service for pub/sub messaging. Use when creating topics, managing subscriptions, configuring message filtering, sending notifications, or setting up mobile push.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.