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 GoldenWing-360/claude-security-skills --skill message-bus-securitygit clone --depth 1 https://github.com/GoldenWing-360/claude-security-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/goldenwing-360/claude-security-skills/message-bus-security)<a href="https://agentmods.dev/skills/goldenwing-360/claude-security-skills/message-bus-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/message-bus-security/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/goldenwing-360/claude-security-skills/message-bus-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/message-bus-security.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 | $0.00086 | $0.02671 |
| Opus 5 | $0.00043 | $0.01336 |
| Sonnet 5 | $0.00017 | $0.00534 |
| Haiku 4.5 | $0.00009 | $0.00267 |
Grade A, and why
message-bus-security 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 11d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Message Bus Security
Message buses (NATS, RabbitMQ, Kafka, MQTT, AWS SQS/SNS, GCP Pub/Sub) are the connective tissue of distributed systems. They're also the most under-audited part of most architectures — by the time the audit gets to "what's on the bus and who can see it", the team has often been on the system for years without revisiting.
This skill is the per-bus and cross-bus checklist. Pairs with distributed-system-audit (system-level audit), agent-client-security (when agents are producers/consumers).
When to invoke
- Introducing a message bus to a new architecture
- Adding multi-tenancy to an existing bus
- After an incident involving cross-tenant leakage, replay, or denial-of-service via the bus
- Auditing a system that uses a bus, especially distributed-agent / IoT / worker-pool architectures
- Periodic review (annually for production buses)
The model
For each bus, you're checking:
- Authentication — who can connect at all
- Authorization — who can publish where, who can subscribe to what
- Tenancy — can tenant A see tenant B's messages, ever
- Confidentiality — in-transit + at-rest encryption
- Integrity / replay — can a captured message be re-sent or forged
- Reliability semantics — exactly-once / at-least-once / at-most-once, and does the application correctly handle the chosen mode
- Audit — when something happens, can you tell who did it
Each bus implements these differently. Below: the common patterns plus per-bus specifics for the three that dominate small/medium-team setups.
NATS
Authentication
NATS has several auth options:
- NKEYs + signed nonces (Ed25519 key-pair per client). Standard for production.
- JWT-based auth (account hierarchy with signed JWTs). Standard for multi-tenant.
- Username/password — for dev only
- TLS client certs — supported; rarely needed when NKEYs are in use
Production pattern: Operator → Accounts → Users. The Operator signs Account JWTs; each Account signs User JWTs. Each User has an NKEY and presents JWT + signed nonce on connect. Revocation is built into the JWT model.
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.
- 11d ago First seen · 249 lines · 86 tokens per session scan A b2db6fab1900
message-bus-security is a skill published in the GitHub repository GoldenWing-360/claude-security-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 2,671 once invoked, about $0.0004 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
tanstack-start
Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 +…
mcp-builder
Build MCP servers in Python with FastMCP. Define tools / resources / prompts, build the server, test locally, deploy to FastMCP Cloud or Docker. Use whenever the user mentions building an MCP server, exposing tools to LLMs, FastMCP, building a Claude integration, or troubleshooting FastMCP module-level server…
hono-api-scaffolder
Scaffold Hono API routes for Cloudflare Workers. Produces route files, middleware, typed bindings, Zod validation, error handling, and APIENDPOINTS.md documentation. Use after a project is set up with cloudflare-worker-builder or vite-flare-starter, when you need to add API routes, create endpoints, or generate API…
cloudflare-worker-builder
Scaffold and deploy Cloudflare Workers with Hono routing, Vite plugin, and Static Assets. Describe project, scaffold structure, configure bindings, deploy. Use whenever the user wants to create a Worker project, set up Hono on Cloudflare, configure D1 / R2 / KV / Queues bindings, or troubleshoot Worker export syntax…
wordpress-setup
Connect to a WordPress site via WP-CLI over SSH or the REST API. Check CLI, test SSH, set up auth, verify access, save config. Use whenever the user wants to connect to a WordPress site, set up WP-CLI access, create an Application Password, or troubleshoot WordPress connection / auth issues.
vite-flare-starter
Scaffold a full-stack Cloudflare app from the vite-flare-starter template — React 19 + Hono + D1+Drizzle + better-auth + Tailwind v4+shadcn/ui + TanStack Query + R2 + Workers AI. Run setup.sh to clone, configure, and deploy. Use whenever the user wants a batteries-included Cloudflare full-stack app, vite-flare-starter…