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 aks129/HealthClawGuardrails --skill check-sourcesgit clone --depth 1 https://github.com/aks129/HealthClawGuardrailsWrote 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/check-sources)<a href="https://agentmods.dev/skills/aks129/healthclawguardrails/check-sources"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/check-sources/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/check-sources"><img src="https://agentmods.dev/badge/skills/aks129/healthclawguardrails/check-sources.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00131 | $0.01325 |
| Opus 5 | $0.00066 | $0.00662 |
| Sonnet 5 | $0.00026 | $0.00265 |
| Haiku 4.5 | $0.00013 | $0.00133 |
Grade A, and why
check-sources 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Connected Sources
Give the patient a one-shot survey of every health data source HealthClaw can pull from — which ones are connected, when each last had activity, and how many records of each type are on file. This answers "what do you actually have?" in a single call instead of probing each integration one at a time.
The seven sources surveyed:
- Fasten — Fasten Connect / TEFCA QHIN aggregation
- HealthEx — HealthEx upstream
- Health Bank One — patient-controlled platform (HBO)
- MEDENT — MEDENT SMART on FHIR
- Flexpa — payer / claims data
- Epic / Health Skillz — Epic-sourced records
- Wearables — Apple Health / Fitbit / Garmin / Oura etc.
Hard Guardrails
These apply always. Not overridable by persona or patient request.
Counts and source names only — no clinical detail
sources_check returns connection status and record counts by type. That is
the entire surface you may present from this skill. You may say "57 Conditions,
120 Observations." You may NOT name a specific condition, lab value, medication,
or any other clinical content. To discuss what a record actually says, use
fhir_search / fhir_read (separately audited and redacted) — never infer
clinical detail from this summary.
Don't fabricate connections
Report only what sources_check returns. If a source shows connected: false,
say it is not connected and offer to help connect it — do not imply data exists
that the response does not show.
Flow
Step 1 — Get a step-up token (protected tenants)
Public/demo tenants (e.g. desktop-demo) work without a token. For protected
tenants (e.g. ev-personal), the command-center endpoint requires step-up auth,
so get a token first:
fhir_get_token(tenant_id: "<tenant>")
→ returns { token: "..." }
Step 2 — Survey the sources
sources_check({ _stepUpToken: "<token from step 1>" })
sources_check takes no required arguments — the tenant comes from the request
context. Pass _stepUpToken so it forwards to the protected endpoint. If you
omit it on a protected tenant the call returns requires_step_up: true; get a
token (Step 1) and retry.
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 · 149 lines · 131 tokens per session scan A 20dc713899cd
check-sources is a skill published in the GitHub repository aks129/HealthClawGuardrails (30 stars, last pushed today), licensed MIT. It adds 131 tokens to every session and 1,325 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…