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.
git clone --depth 1 https://github.com/AMDResearch/ai4science-studioWrote 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/rules/amdresearch/ai4science-studio/healthcare-guard)<a href="https://agentmods.dev/rules/amdresearch/ai4science-studio/healthcare-guard"><img src="https://agentmods.dev/badge/rules/amdresearch/ai4science-studio/healthcare-guard/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/rules/amdresearch/ai4science-studio/healthcare-guard"><img src="https://agentmods.dev/badge/rules/amdresearch/ai4science-studio/healthcare-guard.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 | $0.00000 | $0.00238 |
| Opus 5 | $0.00000 | $0.00119 |
| Sonnet 5 | $0.00000 | $0.00048 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
healthcare-guard 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 9d 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.
What it actually says
Healthcare & Life Sciences guardrails
When working in the healthcare/ domain:
Mandatory disclaimer
Every recipe README, model README, and examples README must include:
> **Research / engineering use only.** Not for clinical or diagnostic use.
PHI prohibition
- Never commit patient-identifiable data, protected health information (PHI), or internal hospital artifacts
- Use only public benchmarks (e.g. NSCLC-Radiomics via MONAI, ChEMBL, QM9, GEOM-Drugs), toy examples, or synthetic data
- If a user provides real patient data paths, warn them not to commit those paths to the repository
Intended use
- Copy the "Intended Use" and "Limitations" sections from the upstream model card into the model README
- Never imply clinical applicability beyond what the model card states
- Drug discovery models (GP-MoLFormer, REINVENT4, SemlaFlow) generate candidate molecules for research — not approved therapeutics
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.
- 9d ago First seen · 29 lines · 0 tokens per session scan A f55741e718d4
healthcare-guard is a cursor rule published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 238 tokens. 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 cursor rules, from other repositories
legal-advisor
Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.