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 resonatehq/resonate-skills --skill resonate-server-natsgit clone --depth 1 https://github.com/resonatehq/resonate-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/resonatehq/resonate-skills/resonate-server-nats)<a href="https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-server-nats"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-server-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/resonatehq/resonate-skills/resonate-server-nats"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-server-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 | $0.00111 | $0.02869 |
| Opus 5 | $0.00056 | $0.01435 |
| Sonnet 5 | $0.00022 | $0.00574 |
| Haiku 4.5 | $0.00011 | $0.00287 |
Grade A, and why
resonate-server-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 12d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resonate on NATS
Overview
resonatehq/resonate-on-nats is a Go server that implements the Resonate protocol on NATS JetStream. JetStream KV holds the state and NATS carries the messages. The server needs no separate database, and it exposes no HTTP interface.
Three things an agent must internalize before writing any code:
- It is not a backend of the core server. There is no flag on
resonatehq/resonatethat produces this. It is a different binary from a different repository. - It is not drop-in. Unlike the ScyllaDB provider, this server has no HTTP interface whatsoever — there is no
net/httpin it.RESONATE_URLis meaningless here. Workers connect over NATS via theNatsNetworkclient. - Only TypeScript and Python can talk to it.
NatsNetworkships in those two SDKs. Go, Rust, and Java have no NATS client, so teams on those languages cannot use this provider. Say so early rather than after they've committed.
Related: resonate-server-scylladb (the drop-in provider), resonate-server-postgres (the protocol inside Postgres, no server process), resonate-server-deployment (core server on systemd).
When to use this skill
- The user already runs NATS and does not want to add a database beside it.
- The user asks whether Resonate can run on NATS or JetStream.
- The user is wiring a worker to an existing
resonate-on-natsdeployment.
When NOT to use this skill
- The user does not already run NATS. Recommend the core server on Postgres — reference implementation, Apache 2.0, what production runs today.
- The user is on Go, Rust, or Java. No NATS client exists in those SDKs. Do not suggest writing one as a workaround.
- The user wants the smallest possible change. The ScyllaDB provider speaks the same HTTP/JSON protocol as the core server, so worker wiring is untouched. This one changes it.
- The user needs promise or task search, or server-side authentication — neither exists here (see Gaps).
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.
- 12d ago First seen · 182 lines · 111 tokens per session scan A c586492f5440
resonate-server-nats is a skill published in the GitHub repository resonatehq/resonate-skills (6 stars, last pushed 21d ago), licensed Apache-2.0. It adds 111 tokens to every session and 2,869 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
workflow
Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow sdk", "queue"…
migrating-workflow-v4-to-v5
Upgrades an app from Workflow SDK 4.x to 5.0. Use when bumping the workflow / @workflow/ dependencies to v5, or when hitting removed v4 APIs — runStep, stepEntrypoint, workflow/internal/private, @workflow/core/private, writeToStream / closeStream / readFromStream on a World, world.steps.get without a runId…
migrating-to-workflow-sdk
Migrates Temporal, Inngest, Trigger.dev, and AWS Step Functions workflows to the Workflow SDK. Use when porting Activities, Workers, Signals, step.run(), step.waitForEvent(), Trigger.dev tasks / wait.forToken / triggerAndWait, ASL JSON state machines, Task/Choice/Wait/Parallel states, task tokens, or child workflows.
deepep-to-cam-converter
A code migration skill for replacing DeepEP communication operations with CAM operations when moving mixture-of-experts code from CUDA/NCCL to Ascend NPUs.
e2a-doctor
Use when an existing e2a MCP connection, inbox, custom domain, protection policy, webhook, or message delivery is failing or unclear. Diagnoses read-only through MCP first, ranks evidence-backed causes, and offers individually confirmed repairs; uses the CLI doctor only when CLI or self-hosted diagnostics are…
e2a-integrate
Use when adding e2a email capabilities to an application or codebase: outbound sending, inbound signed webhooks, REST polling, or SDK integration. Inspects the existing language and framework, uses official TypeScript/Python SDKs or idiomatic REST/OpenAPI, adds tests, and keeps credentials server-side.