agentmods.dev

resonate-server-scylladb

resonate-server-scylladb is a skill for Claude Code, Codex from resonatehq/resonate-skills. It costs 123 tokens per session (3,484 once invoked), scanned B, original, Apache-2.0.

A separate Go server that runs the Resonate protocol using ScyllaDB, a distributed database. Resonate is a system for durable task execution, and this implementation is independent of Resonate’s main Rust server.

In plain words
What is it for?
Use it to set up Resonate with a local or existing ScyllaDB cluster, configure its environment, and use its six-table database schema. Application and worker code can continue using the same HTTP/JSON protocol.
Why use it?
It lets teams with an existing ScyllaDB cluster use Resonate without adding another database. It also clarifies that this requires running a different server, not changing the main server’s storage setting.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is go build -o resonate ./cmd/resonate.

not rated 6repo 21d ago B scan 123 tokens original Apache-2.0

Good fit Use it to set up Resonate with a local or existing ScyllaDB cluster, configure its environment, and use its six-table database schema. Application and worker code can continue using the same HTTP/JSON protocol.

Compare 6 skills from other repositories ↓
View source ↗ resonatehq/resonate-skills
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/resonatehq/resonate-skills
agentmods
npx agentmods add skills/resonatehq/resonate-skills/resonate-server-scylladb

Made for: Claude Code, Codex.

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 resonate-server-scylladb

README.md
[![agentmods](https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-server-scylladb/github.svg)](https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-server-scylladb)
Your own site
<a href="https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-server-scylladb"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-server-scylladb/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.

agentmods 80×15 button for resonate-server-scylladb

Your own site · 80×15
<a href="https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-server-scylladb"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-server-scylladb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,484 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00123 $0.03484
Opus 5 $0.00062 $0.01742
Sonnet 5 $0.00025 $0.00697
Haiku 4.5 $0.00012 $0.00348

Measured 12d ago against content hash 59fe6b5d748e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

resonate-server-scylladb scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -s localhost:8001 -X POST -H 'content-type: application/json' -d '{

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sf localhost:8001/health
resonate-server-scylladb/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resonate on ScyllaDB

Overview

resonatehq/resonate-on-scylladb is a Go server that implements the Resonate protocol against ScyllaDB. It is an independent implementation of the published protocol — not a storage backend of the core Rust server (resonatehq/resonate).

Two consequences an agent must internalize before writing any config:

  1. You cannot get ScyllaDB by configuring the core server. There is no RESONATE_STORAGE__TYPE=scylladb. You run a different binary from a different repository.
  2. It speaks the same HTTP/JSON protocol. Application code, SDK choice, and worker code are unchanged. The only thing that changes is what RESONATE_URL points at.

Related: resonate-server-nats (another provider — NATS-native, not drop-in), resonate-server-postgres (another provider — the protocol inside Postgres, no server process), resonate-server-deployment (core server on systemd), resonate-server-deployment-cloud-run (core server on Cloud Run).

When to use this skill

  • The user already operates a ScyllaDB cluster and does not want to add a database for durable execution.
  • The user asks whether Resonate can run on ScyllaDB or another wide-column store.
  • The user is evaluating durable execution against storage they already run.

When NOT to use this skill

  • The user does not already run ScyllaDB. Recommend the core server on Postgres — it is the reference implementation, it is Apache 2.0, and it is what production deployments run today. Do not steer someone onto ScyllaDB for novelty.
  • The user needs promise or task search — it is unimplemented here (see Gaps).
  • The user is deploying workers, not the server. Worker deployment is unchanged; use the relevant per-SDK skill.

Read the full file on GitHub · 224 lines

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. 12d ago First seen · 224 lines · 123 tokens per session scan B 59fe6b5d748e

Subscribe to this mod's changes

resonate-server-scylladb is a skill published in the GitHub repository resonatehq/resonate-skills (6 stars, last pushed 21d ago), licensed Apache-2.0. It adds 123 tokens to every session and 3,484 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeDatabasesagent-skillsdurable-executionhuman-in-the-loopresonatesaga-pattern
Related

Other skills, from other repositories

golem-add-ignite-rust

Using golem:rdbms/ignite2 from a Rust Golem agent. Use when the user asks to connect to Apache Ignite 2, run SQL over Ignite, or use Ignite from Rust agent code.

golemcloud/golem · 50 tokens

golem-add-postgres-rust

Using golem:rdbms/postgres from a Rust Golem agent. Use when the user asks to connect to PostgreSQL, run SQL, execute a Postgres transaction, or use PostgreSQL from Rust agent code.

golemcloud/golem · 52 tokens

golem-add-ignite-scala

Using Apache Ignite from a Scala Golem agent through golem.host.Rdbms.Ignite. Use when the user asks to connect to Apache Ignite 2, run SQL over Ignite, or use Ignite from Scala agent code.

golemcloud/golem · 54 tokens

golem-add-postgres-ts

Using golem:rdbms/postgres from a TypeScript Golem agent. Use when the user asks to connect to PostgreSQL, run SQL, or use PostgreSQL from TypeScript agent code.

golemcloud/golem · 47 tokens

golem-add-ignite-moonbit

Using golem:rdbms/ignite2 from a MoonBit Golem agent. Use when the user asks to connect to Apache Ignite 2, run SQL over Ignite, or use Ignite from MoonBit agent code.

golemcloud/golem · 53 tokens

golem-add-mysql-moonbit

Using golem:rdbms/mysql from a MoonBit Golem agent. Use when the user asks to connect to MySQL, run SQL, or use MySQL from MoonBit agent code.

golemcloud/golem · 48 tokens