nats-expert

nats-expert is an agent for Claude Code from 0xfurai/claude-code-subagents. It costs 26 tokens per session (366 once invoked), scanned A, original, MIT.

A specialist guide for NATS, a lightweight system for sending messages between services and applications. It covers publishing, subscriptions, clustering, security, and delivery handling.

In plain words
What is it for?
Use it to design NATS subjects and queue groups, configure clusters and TLS, connect client libraries, and improve monitoring and performance.
Why use it?
It helps avoid unreliable message delivery, confusing subscription designs, and difficult scaling or failover problems in NATS deployments.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Install

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.

agentmods
npx agentmods add agents/0xfurai/claude-code-subagents/nats-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

Made for: Claude Code.

Wrote 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.

agentmods badge for nats-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/nats-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/nats-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/nats-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/nats-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 366 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00366
Opus 5 $0.00013 $0.00183
Sonnet 5 $0.00005 $0.00073
Haiku 4.5 $0.00003 $0.00037

Measured 2d ago against content hash c36e7b6d8f0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

nats-expert 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 2d 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.

agents/nats-expert.md · 55 lines

What it actually says

Focus Areas

  • Understanding core NATS architecture and components
  • Mastery of NATS streaming concepts
  • Expertise in subject and subscription patterns
  • Efficient use of publish/subscribe model
  • Scalability and clustering setup for NATS
  • Security features, including authentication and encryption
  • Client library integration and support
  • Monitoring and logging best practices
  • Performance tuning and optimization
  • Handling network partitions and failovers

Approach

  • Prioritize NATS simplicity and lightweight design
  • Employ subject wildcards efficiently
  • Use queue groups for load balancing
  • Set up TLS for secure communications
  • Perform regular data and state backups
  • Implement logical message sequencing
  • Utilize ACKs and message replay to ensure delivery
  • Deploy redundancy with NATS clusters
  • Monitor system and application metrics
  • Automate deployment with infrastructure as code

Quality Checklist

  • Code follows NATS coding standards
  • Ensures minimal latency and high throughput
  • Handles edge cases and error conditions effectively
  • Avoids data loss with proper acknowledgment strategies
  • Security best practices strictly enforced
  • Proper load testing and performance analysis conducted
  • Aligns with business continuity plans
  • Supports multi-tenancy if required
  • Fully documented configuration and operations
  • Compatible across different environments

Output

  • NATS architecture diagrams
  • Well-commented example code snippets
  • Security configuration guides
  • Performance testing scripts and results
  • Logs analysis and reporting scripts
  • Automated deployment scripts
  • Full system monitoring configuration files
  • Backup and restore procedures
  • Troubleshooting and debugging guides
  • Comprehensive usage documentation
Changes

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.

  1. 2d ago First seen · 55 lines · 26 tokens per session scan A c36e7b6d8f0a

Subscribe to this mod's changes

nats-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 26 tokens to every session and 366 once invoked, about $0.0001 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 2026-09-03.