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 Neeeophytee/agent-stylebooks --skill nhs-health-contentgit clone --depth 1 https://github.com/Neeeophytee/agent-stylebooksWrote 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/neeeophytee/agent-stylebooks/nhs-health-content)<a href="https://agentmods.dev/skills/neeeophytee/agent-stylebooks/nhs-health-content"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/nhs-health-content/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/neeeophytee/agent-stylebooks/nhs-health-content"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/nhs-health-content.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 | $0.00067 | $0.00863 |
| Opus 5 | $0.00034 | $0.00432 |
| Sonnet 5 | $0.00013 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
nhs-health-content 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NHS health content
Help patients and the public find clinically important information and decide what to do next. Write for the person's need and circumstances, not the healthcare system's structure.
Establish the clinical boundary
- Use only current, recognized evidence and verified service information supplied for the task.
- Preserve clinical qualifiers, contraindications, safety-netting, dose or timing details, eligibility, and limits on service availability.
- Do not infer a diagnosis from incomplete symptoms or imply that content replaces assessment by a qualified healthcare professional.
- Keep medical uncertainty visible. Distinguish
can,may,usually, andwill. - Send unresolved factual or safety questions for clinical review; do not smooth them over.
Start with the patient need
- Identify the patient group, their likely situation, and the question they need answered.
- Decide the page's primary job: recognize, prepare, choose, act, recover, or seek help.
- Put the answer or clinically important next action near the beginning.
- Order supporting information by the patient's journey, not by specialty or organization.
- Separate common information from routes that apply only to particular people.
Make urgency unmistakable
- Keep emergency, urgent, and routine advice in separate, clearly labelled sections.
- Name the observable sign or situation that triggers each route.
- State the action, channel, and timing together. Preserve the exact service and geography.
- Put urgent safety advice before self-care detail or background.
- Include safety-netting: what change should prompt the person to seek more help.
- Never intensify or reduce urgency without verified clinical authority.
Explain conditions and treatment
- Use familiar language first. Add an unfamiliar clinical term in parentheses when it helps recognition, search, or a conversation with a clinician.
- Describe symptoms without implying that one symptom proves a condition.
- Separate what a treatment is for, what it involves, likely benefits, material risks, alternatives, and what remains uncertain.
- Explain preparation, what happens, aftercare, and whom to contact about problems.
- Use absolute numbers with a population and time frame when the evidence provides them.
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 · 83 lines · 67 tokens per session scan A ca7920f77261
nhs-health-content is a skill published in the GitHub repository Neeeophytee/agent-stylebooks (61 stars, last pushed 20d ago), licensed MIT. It adds 67 tokens to every session and 863 once invoked, about $0.0003 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
yolo-training
This skill should be used when user asks to "improve my mAP", "why is my model overfitting", "my training is diverging", "read my results.csv", "interpret my training curves", "my AP50 is good but AP50-95 is bad", "my recall is low", "how do I pick learning rate", "which augmentations should I use", "should I use a…
paper-search-usage
This skill should be used when user asks to "search for papers", "find research papers", "search arXiv", "search PubMed", "find academic papers", "search IEEE", "search Scopus", or "look up scientific literature".
openevidence
Query OpenEvidence (clinical evidence assistant) without an MCP server. Closely mirrors the openevidence-mcp tool surface - check auth, list question history, fetch an article, or ask a new question (with optional follow-up thread). Use when the user asks medical / evidence-based clinical questions, references…
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
adaptyv
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API…
claude-ally-health
A health assistant skill for medical information analysis, symptom tracking, and wellness guidance.