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/briiirussell/cybersecurity-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/rules/briiirussell/cybersecurity-skills/security-comms)<a href="https://agentmods.dev/rules/briiirussell/cybersecurity-skills/security-comms"><img src="https://agentmods.dev/badge/rules/briiirussell/cybersecurity-skills/security-comms/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/briiirussell/cybersecurity-skills/security-comms"><img src="https://agentmods.dev/badge/rules/briiirussell/cybersecurity-skills/security-comms.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 | $0.00150 | $0.03313 |
| Opus 5.5 | $0.00060 | $0.01325 |
| Sonnet 5.5 | $0.00030 | $0.00663 |
| Haiku 4.5 | $0.00015 | $0.00331 |
Grade A, and why
security-comms 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 today.
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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Comms — Translating Security Work for Non-Security Audiences
The skill that closes the gap every other skill produces. The audit family generates findings; the response family generates incidents; the governance family generates roadmaps. None of those outputs survive contact with a board, a customer, a sales engineer trying to answer a security questionnaire, or a CFO asking "is this going to cost us money."
This skill takes technical security work and turns it into the deliverable that audience can actually use. It's the skill security practitioners reach for two to three times a week and that founders without dedicated security teams reach for whenever a finding has to leave the security context.
Cross-references: feeds from every other skill (audit output, incident write-ups, threat-model summaries, CSF assessments) and produces audience-specific deliverables; pairs especially closely with finding-triage (the disposition writeup) and incident-triage (the response narrative).
Authorization
Draft communications for the user's own organization, from facts they provide. A draft is not approval to send: anything external (customers, regulators, press, a researcher) needs sign-off from the owner the plan names, and breach notifications need legal review. Don't put customer names, PII or unconfirmed details in a draft without that sign-off.
The seven audiences (and what each one actually needs)
Security comms is not one register. Each audience needs a different deliverable; using the wrong register is the most common failure mode.
1. Board of directors / non-executive directors
They need to know: Are we materially exposed? Is the team handling it? Is more investment needed?
They do not need: CVE numbers, file paths, scanner names, technical jargon, the methodology.
Format: One slide or one page. Three sections — current posture in one paragraph, top three risks with one sentence each, named investments / decisions needed. Numbers must be material (in dollars or % impact), not raw counts ("we have 47 vulnerabilities" tells them nothing; "two of our payments-team services have unpatched issues an attacker could use to access customer card data" tells them what to do).
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.
- today Changed · +4 lines · -3 tokens per session 22e240c3f006
- 1mo ago First seen · 290 lines · 153 tokens per session scan A eca3eab89619
security-comms is a cursor rule published in the GitHub repository briiirussell/cybersecurity-skills (435 stars, last pushed today), licensed MIT. It adds 150 tokens to every session and 3,313 once invoked, about $0.0006 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 2026-08-30.
Other cursor rules, from other repositories
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.
no-family-vocabulary-in-framework
The framework domain (packages/1-framework) carries no family- or target-specific vocabulary — types, fields, hooks, or strategy values — and, outside the CLI and the PSL parser's grammar names, no Prisma version name before 8. Enforced by the no-family-vocabulary Biome plugin plus the lint:ratchets ratchet.