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 2023Anita/clinical-ai-agent-skills --skill clinical-research-safetygit clone --depth 1 https://github.com/2023Anita/clinical-ai-agent-skillsWrote 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/2023anita/clinical-ai-agent-skills/clinical-research-safety)<a href="https://agentmods.dev/skills/2023anita/clinical-ai-agent-skills/clinical-research-safety"><img src="https://agentmods.dev/badge/skills/2023anita/clinical-ai-agent-skills/clinical-research-safety/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/2023anita/clinical-ai-agent-skills/clinical-research-safety"><img src="https://agentmods.dev/badge/skills/2023anita/clinical-ai-agent-skills/clinical-research-safety.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 | $0.00034 | $0.00261 |
| Opus 5.5 | $0.00014 | $0.00104 |
| Sonnet 5.5 | $0.00007 | $0.00052 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
clinical-research-safety 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 1mo 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
Clinical Research Safety
Goal
Keep clinical research and medical AI work evidence-aware, scoped, and clearly separate from patient-specific medical advice.
Required Behavior
- Identify whether the task is research, education, documentation, or engineering.
- Refuse to provide patient-specific diagnosis, treatment, dosing, triage, or clinical decision support.
- Separate facts, inference, and suggestions.
- Mark unverified claims as unverified.
- Recommend qualified clinical review when content could affect health decisions.
Output Pattern
Use this structure when summarizing medical content:
## Purpose
Research / education / documentation / engineering assistance.
## Source Facts
- Fact supported by the provided source.
## Interpretation
- Careful inference from the source facts.
## Uncertainty
- What is missing, weak, or unverified.
## Safety Note
This is not patient-specific medical advice and requires qualified clinical review.
Do Not
- Invent citations or guidelines.
- Convert population-level evidence into patient-level advice.
- Ask for private patient records.
- Hide uncertainty.
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.
- 1mo ago First seen · 48 lines · 34 tokens per session scan A 4e0c7affe0cd
clinical-research-safety is a skill published in the GitHub repository 2023Anita/clinical-ai-agent-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 261 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
meta-analysis
Use when running a systematic review and meta-analysis, DTA or intervention. Covers PROSPERO protocol, search, screening, extraction, risk of bias (QUADAS-3, RoB 2, ROBINS-I), bivariate/HSROC or random-effects pooling, forest plots, heterogeneity and PRISMA reporting. Topic scouting is /ma-scout.
present-paper
Use when preparing an academic talk such as a journal club, grand rounds, seminar, conference presentation, or lecture/teaching deck. Analyzes the source, drafts audience-adapted speaker scripts, builds or augments the PPTX with speaker notes and prepares Q&A.
write-paper
Use when drafting a medical research manuscript or any IMRAD section. Runs an 8-phase pipeline from outline to submission-ready draft for original articles, AI validation studies, case reports, meta-analyses, technical notes and more. Checking a draft is /self-review.
analyze-stats
Use when data needs statistical analysis. Runs reproducible Python/R code for Table 1, diagnostic accuracy, agreement, regression, survival, propensity score, survey-weighted and repeated-measures models, with publication tables. Sample size is /calc-sample-size; pooling studies is /meta-analysis.
check-reporting
Use when auditing a manuscript item by item against a reporting guideline or risk-of-bias tool. Covers 49 reporting guidelines and risk-of-bias tools (STROBE, CONSORT, STARD, TRIPOD+AI, PRISMA, QUADAS and more), marking each item PRESENT, PARTIAL or MISSING. Not a reviewer critique (/self-review).
sync-submission
Use when building, auditing or freezing a journal submission package from the canonical manuscript. Detects drift between the source and the per-journal submission copy, builds byte-preserving packages with manifests, and records current, stale or frozen status.