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 cdc-clear-communicationgit 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/cdc-clear-communication)<a href="https://agentmods.dev/skills/neeeophytee/agent-stylebooks/cdc-clear-communication"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/cdc-clear-communication/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/cdc-clear-communication"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/cdc-clear-communication.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 | $0.00064 | $0.00845 |
| Opus 5 | $0.00032 | $0.00423 |
| Sonnet 5 | $0.00013 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
cdc-clear-communication 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 10d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CDC clear communication
Help a defined public audience notice, understand, and act on accurate health information. Treat clarity as part of safety, not as permission to weaken evidence.
Protect health and scientific truth
- Preserve verified symptoms, thresholds, populations, time windows, contraindications, uncertainties, and instructions exactly.
- Do not diagnose, prescribe, infer causation, or add a benefit or risk that the source material does not support.
- Separate established evidence, preliminary findings, expert judgment, and unknowns.
- Identify the authority and date for advice that may change during an incident.
- Flag contradictions or missing clinical review instead of resolving them through prose.
Set the communication contract
- Name one primary audience and the situation in which they will receive the material.
- State the communication objective as an observable outcome: what the audience should know, decide, or do.
- Write one primary message that combines the most important fact with its relevance.
- Put that message at the beginning. Do not make readers assemble it from several sections.
- Identify the primary action and any deadline, trigger, location, or source of help.
When several audiences need different actions, create separate routes or separate products. Do not dilute the primary message into a list of equally weighted points.
Make action possible
- Begin each recommendation with a concrete verb and name who should act.
- Place prerequisites and supplies before the action that depends on them.
- Explain why an action matters when the reason affects trust, urgency, or adherence.
- Distinguish required action, recommended action, and optional information.
- For emergency material, lead with the danger signal and immediate action. Put background after the route to safety.
- Give a fallback when the primary channel, service, or resource may be unavailable.
Explain health information
- Use words the audience is likely to use. Keep an exact clinical term when it helps a person recognize what a clinician may say, and explain it at first use.
- Prefer concrete subjects and active constructions. Name the agency, clinician, condition, or treatment that acts.
- Use headings that answer audience questions and lists that expose actions or choices.
- Keep cautions beside the claim or action they qualify.
- Use a visual only when it carries part of the message; provide a caption or text alternative that states the relevant meaning.
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.
- 10d ago First seen · 82 lines · 64 tokens per session scan A ff07ae3a5c36
cdc-clear-communication is a skill published in the GitHub repository Neeeophytee/agent-stylebooks (60 stars, last pushed 17d ago), licensed MIT. It adds 64 tokens to every session and 845 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
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…
lov-thesis-polish
An academic editing tool for improving an MBA thesis or dissertation in Markdown, a plain-text format for structured documents. It addresses language, argument structure, logic, research contributions, and formatting.
learning-assistant
An interactive study assistant that turns a learning goal into a structured plan and guides the learner through it. It uses a local knowledge graph, a connected record of topics and learning state, as its long-term memory.
reading-notes
Process a book or article into structured progressive summary notes saved to the resources folder. Use when the user has finished reading something and wants to capture structured notes — 'I just finished reading X', 'take notes on this book'. Do NOT use for: fetching and summarizing a URL now (use summarize)…