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-postgresgit 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-postgres)<a href="https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-server-postgres"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-server-postgres/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-postgres"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-server-postgres.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 | $0.00112 | $0.03067 |
| Opus 5 | $0.00056 | $0.01533 |
| Sonnet 5 | $0.00022 | $0.00613 |
| Haiku 4.5 | $0.00011 | $0.00307 |
Grade A, and why
resonate-server-postgres 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resonate on Postgres
Overview
resonatehq/resonate-pg implements the Resonate protocol as a schema of PL/pgSQL stored procedures. You load one file into a Postgres 16+ database and the database is the server — storage, queue, and timer, with pg_cron driving all three.
Three things an agent must internalize before writing any code:
- It is not the core server on Postgres. Those are different things and users conflate them constantly. The core server supports Postgres: you run a binary and Postgres holds its state.
resonate-pgis Postgres: there is no binary, no process, and no port. If the user wants a Resonate server that stores data in Postgres, send them to the core server instead — it is more mature and every SDK can talk to it. - It is not drop-in, and there is no URL. There is no HTTP server, so
RESONATE_URLis meaningless. Workers reach the protocol by callingresonate.resonate_rpc(jsonb)over a database connection, which needs a client that speaks SQL. - One client exists, and it targets Deno.
@resonatehq/supabaseon JSR is the only implementation. Python, Go, Rust, and Java have nothing, and each is tracked as an open issue. Say this before the user commits, not after.
Related: resonate-supabase-deployments-typescript (deploying workers as Edge Functions against this server), resonate-server-nats and resonate-server-scylladb (the other two providers), resonate-server-deployment (core server on systemd).
Scope boundary: this skill covers the server — installing it, what it implements, how to operate it. For wiring and deploying a worker against it, use the Supabase deployments skill above.
When to use this skill
- The user already runs Postgres and does not want to deploy a process beside it.
- The user asks whether Resonate can run on Supabase, or "just in my database."
- The user is operating an existing
resonate-pginstall — timers, retention, grants.
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 · 163 lines · 112 tokens per session scan A 1fce74a1f9c8
resonate-server-postgres is a skill published in the GitHub repository resonatehq/resonate-skills (6 stars, last pushed 19d ago), licensed Apache-2.0. It adds 112 tokens to every session and 3,067 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
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.
golem-add-postgres-scala
Using PostgreSQL from a Scala Golem agent through golem.host.Rdbms.Postgres. Use when the user asks to connect to PostgreSQL, run SQL, or use Postgres from Scala agent code.
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.
golem-add-postgres-moonbit
Using golem:rdbms/postgres from a MoonBit Golem agent. Use when the user asks to connect to PostgreSQL, run SQL, or use PostgreSQL from MoonBit agent code.
postgres-safety
What is genuinely irreversible in PostgreSQL, which DDL takes which lock, and when a statement rewrites the whole table. Load before writing or reviewing any migration.
postgres-patterns
Provides PostgreSQL patterns for query optimization, schema design, indexing strategies, RLS, and security. Use when working with PostgreSQL SQL files or when the user mentions PostgreSQL, Postgres, pgvector, Supabase, or database optimization.