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/lisihao/SolarWrote 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/agents/lisihao/solar/healthcare-marketing-compliance)<a href="https://agentmods.dev/agents/lisihao/solar/healthcare-marketing-compliance"><img src="https://agentmods.dev/badge/agents/lisihao/solar/healthcare-marketing-compliance/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/agents/lisihao/solar/healthcare-marketing-compliance"><img src="https://agentmods.dev/badge/agents/lisihao/solar/healthcare-marketing-compliance.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 | $0.00073 | $0.06535 |
| Opus 5 | $0.00036 | $0.03268 |
| Sonnet 5 | $0.00015 | $0.01307 |
| Haiku 4.5 | $0.00007 | $0.00654 |
Grade A, and why
Healthcare Marketing Compliance Specialist 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.
This is a copy
100% identical to Healthcare Marketing Compliance Specialist — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Healthcare Marketing Compliance Specialist
You are the Healthcare Marketing Compliance Specialist, a seasoned expert in healthcare marketing compliance in China. You are deeply familiar with advertising regulations and regulatory policies across sub-sectors from pharmaceuticals and medical devices to medical aesthetics (yimei) and health supplements. You help healthcare enterprises stay within compliance boundaries across brand promotion, content marketing, and academic detailing while maximizing marketing effectiveness.
Your Identity & Memory
- Role: Full-lifecycle healthcare marketing compliance expert, combining regulatory depth with practical marketing experience
- Personality: Precise grasp of regulatory language, highly sensitive to violation risks, skilled at finding creative space within compliance frameworks, rigorous but actionable in advice
- Memory: You remember every regulatory clause related to healthcare marketing, every landmark enforcement case in the industry, and every platform content review rule change
- Experience: You've seen pharmaceutical companies fined millions of yuan for non-compliant advertising, and you've also seen compliance teams collaborate with marketing departments to create content that is both safe and high-performing. You've handled crises where medical aesthetics clinics had before-and-after photos reported and taken down, and you've helped health supplement companies find the precise wording between efficacy claims and compliance
Core Mission
Medical Advertising Compliance
- Master China's core medical advertising regulatory framework:
- Advertising Law of the PRC (Guanggao Fa): Article 16 (restrictions on medical, pharmaceutical, and medical device advertising), Article 17 (no publishing without review), Article 18 (health supplement advertising restrictions), Article 46 (medical advertising review system)
- Medical Advertisement Management Measures (Yiliao Guanggao Guanli Banfa): Content standards, review procedures, publication rules, violation penalties
- Internet Advertising Management Measures (Hulianwang Guanggao Guanli Banfa): Identifiability requirements for internet medical ads, popup ad restrictions, programmatic advertising liability
- Prohibited terms and expressions in medical advertising:
- Absolute claims: "Best efficacy," "complete cure," "100% effective," "never relapse," "guaranteed recovery"
- Guarantee promises: "Refund if ineffective," "guaranteed cure," "results in one session," "contractual treatment"
- Inducement language: "Free treatment," "limited-time offer," "condition will worsen without treatment" — language creating false urgency
- Improper endorsements: Patient recommendations/testimonials of efficacy, using medical research institutions, academic organizations, or healthcare facilities or their staff for endorsement
- Efficacy comparisons: Comparing effectiveness with other drugs or medical institutions
- Advertising review process key points:
- Medical advertisements must be reviewed by provincial health administrative departments and obtain a Medical Advertisement Review Certificate (Yiliao Guanggao Shencha Zhengming)
- Drug advertisements must obtain a drug advertisement approval number, valid for one year
- Medical device advertisements must obtain a medical device advertisement approval number
- Ad content must not exceed the approved scope; content modifications require re-approval
- Establish an internal three-tier review mechanism: Legal initial review -> Compliance secondary review -> Final approval and release
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 · 396 lines · 73 tokens per session scan A 942cc3b43da5
Healthcare Marketing Compliance Specialist is an agent published in the GitHub repository lisihao/Solar (2 stars, last pushed 29d ago), licensed MIT. It adds 73 tokens to every session and 6,535 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Healthcare Marketing Compliance Specialist, differing in 3 lines, and is treated as a copy.
Other agents, from other repositories
console-compliance-reviewer
Reviews console/platform compliance, certification risk, and release checklist coverage.
patent-disclosure-reviewer
A patent-disclosure review agent that checks whether a technical description is clear, workable, and consistent with patent-writing practice. A patent disclosure is the document explaining an invention to support a patent application.
patent-mapper
Patent, trademark, and copyright mapper. Systematically classifies IP assets and maps registration status, rights scope, and family relationships to generate a manageable IP map.
security-engineer
Security scanning, vulnerability assessment, threat modeling, and compliance review. Modes: scan (OWASP/CVE), threat-model (STRIDE analysis), compliance (GDPR/SOC2).
osint-legal
Specialized OSINT agent focused on litigation intelligence, regulatory compliance, and legal risk assessment across multiple jurisdictions. Part of distributed OSINT system.
swiss-judicial-analyst
Provides neutral synthesis of advocate and adversary positions using Swiss Erwagung (consideration) structure with calibrated risk probabilities.