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 kaustavdm/nats-skill --skill natsgit clone --depth 1 https://github.com/kaustavdm/nats-skillWrote 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/kaustavdm/nats-skill/nats)<a href="https://agentmods.dev/skills/kaustavdm/nats-skill/nats"><img src="https://agentmods.dev/badge/skills/kaustavdm/nats-skill/nats/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/kaustavdm/nats-skill/nats"><img src="https://agentmods.dev/badge/skills/kaustavdm/nats-skill/nats.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 | $0.00048 | $0.03895 |
| Opus 5 | $0.00024 | $0.01947 |
| Sonnet 5 | $0.00010 | $0.00779 |
| Haiku 4.5 | $0.00005 | $0.00390 |
Grade A, and why
nats 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 9d 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 — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NATS Development Reference
Docs: https://docs.nats.io | Examples: https://natsbyexample.com
NATS is a subject-based connective layer for distributed systems. Messages route by subject string, not hostname:port. Server binary is ~20MB, runs on Raspberry Pi to cloud. CNCF project, Apache 2.0 licensed, 40+ client libraries. Max message payload: 1MB default (configurable up to 64MB; keep under ~8MB in practice).
Two planes — choose before designing:
| Plane | Delivery | Persistence | Use for |
|---|---|---|---|
| Core NATS | At-most-once | None | Fire-and-forget, RPC, real-time fan-out |
| JetStream | At-least/exactly-once | Streams | Durable queues, replay, KV state, work queues |
Deep reference files in references/:
jetstream.md— full StreamConfig/ConsumerConfig fields, async publish, KV/object-store opsserver-deployment.md— full config options, Docker, Kubernetes, Go embedding structsecurity.md— NKey, JWT/operator model, nsc CLI, TLS, auth callout
Subjects
→ https://docs.nats.io/nats-concepts/subjects
service.orders.created # exact (publishers always use exact subjects)
service.orders.* # * = one token (subscribers only)
service.orders.> # > = one or more tokens at end (subscribers only)
- Dot-separated hierarchy; max 16 tokens, <256 chars recommended
- Alphanumeric,
-,_only (avoid other special chars) $prefix reserved for system use ($SYS.*,$JS.*,$KV.*,$SRV.*)- Multiple overlapping subs on one connection → duplicate delivery per matching sub
Core NATS Patterns
→ https://docs.nats.io/nats-concepts/core-nats
Pub/Sub
Fan-out to all subscribers. Zero config — subjects are ephemeral.
nc.Publish("orders.created", data)
nc.Subscribe("orders.*", func(msg *nats.Msg) { /* handle */ })
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.
- 9d ago First seen · 454 lines · 48 tokens per session scan A 106696625691
nats is a skill published in the GitHub repository kaustavdm/nats-skill (15 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 3,895 once invoked, about $0.0002 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
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
cognito
AWS Cognito user authentication and authorization service. Use when setting up user pools, configuring identity pools, implementing OAuth flows, managing user attributes, or integrating with social identity providers.
sns
AWS SNS notification service for pub/sub messaging. Use when creating topics, managing subscriptions, configuring message filtering, sending notifications, or setting up mobile push.
liveview-patterns
Build LiveView: async data (assignasync), PubSub (check connected?), phx-change events, form components/modals/uploads, streams for lists, livepatch. Use when handling interactions, debugging events, or tracking Presence.