gorse-clickhouse-cloud-incompatible

gorse-clickhouse-cloud-incompatible is a skill for Claude Code, Codex from divinevideo/divine-mobile. It costs 122 tokens per session (798 once invoked), scanned A, original, MPL-2.0.

A troubleshooting guide for connecting Gorse, a recommendation engine, to ClickHouse Cloud, a hosted analytics database.

In plain words
What is it for?
Use it to check Gorse’s ClickHouse protocol, port, and connection-string compatibility when deploying with ClickHouse Cloud.
Why use it?
It explains why the connection can fail with an EOF error even when the TLS connection itself works.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

Good fit Use it to check Gorse’s ClickHouse protocol, port, and connection-string compatibility when deploying with ClickHouse Cloud.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/divinevideo/divine-mobile/gorse-clickhouse-cloud-incompatible
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.

Any agent
npx skills add divinevideo/divine-mobile --skill gorse-clickhouse-cloud-incompatible
Clone the repo
git clone --depth 1 https://github.com/divinevideo/divine-mobile

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 gorse-clickhouse-cloud-incompatible

README.md
[![agentmods](https://agentmods.dev/badge/skills/divinevideo/divine-mobile/gorse-clickhouse-cloud-incompatible/github.svg)](https://agentmods.dev/skills/divinevideo/divine-mobile/gorse-clickhouse-cloud-incompatible)
Your own site
<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/gorse-clickhouse-cloud-incompatible"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/gorse-clickhouse-cloud-incompatible/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 gorse-clickhouse-cloud-incompatible

Your own site · 80×15
<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/gorse-clickhouse-cloud-incompatible"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/gorse-clickhouse-cloud-incompatible.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00122 $0.00798
Opus 5 $0.00061 $0.00399
Sonnet 5 $0.00024 $0.00160
Haiku 4.5 $0.00012 $0.00080

Measured 7d ago against content hash d942f056b542, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gorse-clickhouse-cloud-incompatible 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 7d 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/skills/gorse-clickhouse-cloud-incompatible/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gorse + ClickHouse Cloud Incompatibility

Problem

Gorse recommendation engine fails to connect to ClickHouse Cloud with EOF errors during protocol negotiation, even though TLS handshake succeeds.

Context / Trigger Conditions

  • Gorse master/server pods show CrashLoopBackOff
  • Logs show: failed to connect data database: EOF or transport failed to send a request to ClickHouse: EOF
  • Using ClickHouse Cloud (*.clickhouse.cloud) as the GORSE_DATA_STORE
  • TLS connection works when tested with openssl s_client
  • Tried various connection parameters without success

Root Cause

Despite the clickhouse:// URL scheme suggesting native protocol, Gorse actually uses the HTTP interface on port 8123 (not the native protocol on port 9000/9440). ClickHouse Cloud's HTTP interface on port 8443 has compatibility issues with Gorse's driver.

Key facts:

  • Gorse uses ClickHouse HTTP interface (port 8123), NOT native protocol (port 9000)
  • ClickHouse Cloud port 8443: HTTP/HTTPS protocol
  • ClickHouse Cloud port 9440: Native protocol with TLS
  • Gorse only accepts: clickhouse://, mysql://, postgres://, mongodb://
  • Gorse does NOT support https:// scheme (returns "unsupported data storage backend")
  • Redis is only for cache store, NOT data store
  • If you use port 9000 with in-cluster ClickHouse, you'll get: "Port 9000 is for clickhouse-client program. You must use port 8123 for HTTP."

Solution Options

Option 1: Use In-Cluster ClickHouse (Recommended)

Deploy ClickHouse Operator with an in-cluster instance for Gorse:

# Standard in-cluster connection works
GORSE_DATA_STORE: "clickhouse://user:password@clickhouse-host:8123/gorse"

Option 2: Use Different Database

Gorse supports MySQL and PostgreSQL as data stores:

GORSE_DATA_STORE: "mysql://user:password@host:3306/gorse"
# or
GORSE_DATA_STORE: "postgres://user:password@host:5432/gorse"

Option 3: Deploy ClickHouse Proxy

Set up a proxy (like chproxy) that translates between protocols.

Read the full file on GitHub · 80 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. 7d ago First seen · 80 lines · 122 tokens per session scan A d942f056b542

Subscribe to this mod's changes

gorse-clickhouse-cloud-incompatible is a skill published in the GitHub repository divinevideo/divine-mobile (265 stars, last pushed today), licensed MPL-2.0. It adds 122 tokens to every session and 798 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 2026-09-03.

Related

Other skills, from other repositories

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens

convex-explain-app

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

openclaw/clawhub · 47 tokens

platform-custom-field-generate

Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…

forcedotcom/sf-skills · 194 tokens

field-service-sobject-create-configure

Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…

forcedotcom/sf-skills · 74 tokens

durable-objects

Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

fcakyon/claude-codex-settings · 22 tokens

nornicdb-grpc

Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…

orneryd/NornicDB · 98 tokens